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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 999
    Prev
    Next
    INDEX
    Explanations

    negative statements or contradictions

    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
    1438
    +0.11
    0.3%
    270
    +0.09
    0.2%
    474
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.11
    0.07
    270
    +0.09
    0.05
    1087
    +0.09
    0.03
    Negative Logits
     embra
    -1.02
     milf
    -0.99
     inev
    -0.96
     perfet
    -0.94
     shenan
    -0.93
     affor
    -0.92
     inconce
    -0.91
     intersper
    -0.91
     emphat
    -0.90
     excru
    -0.90
    POSITIVE LOGITS
     nor
    0.86
     tampoco
    0.74
     siquiera
    0.68
    RTGC
    0.65
     even
    0.64
    nor
    0.64
     anything
    0.62
     any
    0.62
    DebuggerNonUser
    0.59
    even
    0.59
    Activations Density 0.461%

    No Known Activations