© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 4574
    Prev
    Next
    INDEX
    Explanations

    the words related to legal investigations or inquiries

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1056
    +0.11
    0.3%
    1499
    +0.09
    0.2%
    214
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1056
    +0.11
    0.04
    1088
    +0.09
    0.04
    223
    +0.08
    0.03
    Negative Logits
     impra
    -1.26
     desir
    -1.18
     emphat
    -1.17
     thut
    -1.15
     increa
    -1.14
     inev
    -1.13
     madonna
    -1.11
     suscep
    -1.11
     effe
    -1.11
     eiffel
    -1.10
    POSITIVE LOGITS
     allegations
    0.76
     investigate
    0.66
     investigating
    0.65
     investigation
    0.62
     investigations
    0.61
     whether
    0.61
    fjspx
    0.61
     investigates
    0.59
    piram
    0.59
     архивлан
    0.58
    Activations Density 0.205%

    No Known Activations