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

    Neuronpedia

    Jacobian LensNEW
    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. 14870
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and settlement matters

    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
    1978
    +0.19
    0.6%
    1967
    +0.18
    0.5%
    453
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.19
    0.04
    1597
    +0.18
    0.03
    276
    +0.16
    0.03
    Negative Logits
    zwungen
    -0.67
     contextLoads
    -0.61
    fährt
    -0.59
    knitted
    -0.57
    pullover
    -0.57
     fået
    -0.57
    Przyp
    -0.57
    Dlaczego
    -0.56
    Waarom
    -0.56
     overcrow
    -0.56
    POSITIVE LOGITS
     alkoh
    1.25
     kosme
    1.20
     silikon
    1.19
     keramik
    1.17
     akut
    1.16
     optik
    1.15
     karton
    1.14
     antik
    1.14
     konkre
    1.11
     reger
    1.08
    Activations Density 0.116%

    No Known Activations