© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14446
    Prev
    Next
    INDEX
    Explanations

    expressions of personal reflection and evaluation of experiences

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EDEFAULT
    -0.85
    IntoConstraints
    -0.63
     RouterModule
    -0.61
    cloudfront
    -0.60
    UnusedPrivate
    -0.57
    CodeAttribute
    -0.54
     législation
    -0.53
    ngdoc
    -0.49
     bäst
    -0.48
     lunares
    -0.47
    POSITIVE LOGITS
    addElement
    0.75
    adə
    0.56
     var
    0.54
    مني
    0.54
    hObject
    0.54
    DMETHOD
    0.54
     Var
    0.53
    AMENTE
    0.52
    <%=
    0.50
     interact
    0.50
    Activations Density 0.165%

    No Known Activations