© 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. 23618
    Prev
    Next
    INDEX
    Explanations

    statements or phrases indicating causality or logical conclusion

    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
    GN
    -0.69
    DrawerToggle
    -0.68
     externi
    -0.64
    gn
    -0.63
    EndContext
    -0.63
    BackgroundImage
    -0.63
    ろ
    -0.63
    Gros
    -0.62
     HRS
    -0.62
    Sc
    -0.59
    POSITIVE LOGITS
    olesale
    0.77
    antMatchers
    0.74
    ponents
    0.73
     виправивши
    0.72
    لاعب
    0.71
    ñoz
    0.71
    valents
    0.71
    tiérrez
    0.69
     Miy
    0.69
     dairy
    0.68
    Activations Density 0.007%

    No Known Activations