© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12893
    Prev
    Next
    INDEX
    Explanations

    phrases related to covering up information or hiding wrongdoing

    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
    468
    +0.11
    0.3%
    2004
    +0.09
    0.3%
    890
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2004
    +0.11
    0.04
    468
    +0.09
    0.03
    549
    +0.08
    0.03
    Negative Logits
     shenan
    -1.70
     reluct
    -1.64
     impra
    -1.58
     increa
    -1.54
     disagre
    -1.52
     affor
    -1.52
     volunte
    -1.50
     inev
    -1.49
     uninten
    -1.47
     snoopy
    -1.47
    POSITIVE LOGITS
    hide
    0.71
    MethodManager
    0.68
     hide
    0.67
     typelib
    0.65
     hidden
    0.63
    hidden
    0.62
     ModelExpression
    0.59
    cover
    0.58
     nawr
    0.57
    rrggbb
    0.57
    Activations Density 0.170%

    No Known Activations