© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30192
    Prev
    Next
    INDEX
    Explanations

    statements of personal experience or opinion

    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
     aprendido
    -0.62
     confession
    -0.57
    dymyr
    -0.54
    xaml
    -0.52
    Abitanti
    -0.52
     moks
    -0.51
     AdapterView
    -0.50
    endsection
    -0.49
    addError
    -0.49
    Bromoform
    -0.49
    POSITIVE LOGITS
    SharedCtor
    0.70
    VersionUID
    0.60
    verifyException
    0.59
    StoryboardSegue
    0.58
    URLException
    0.57
     beginnetje
    0.54
    OrBuilder
    0.53
    ArgumentParser
    0.53
    NameInMap
    0.53
    migrationBuilder
    0.52
    Activations Density 0.037%

    No Known Activations