© 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. 14813
    Prev
    Next
    INDEX
    Explanations

    references to figures and citations in the text

    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
     noting
    -0.56
     thinking
    -0.55
     considering
    -0.54
    lück
    -0.50
     thoughts
    -0.50
     saying
    -0.47
     thought
    -0.46
     note
    -0.45
     wondering
    -0.45
     stating
    -0.45
    POSITIVE LOGITS
     nahilalakip
    0.94
    parsedMessage
    0.91
    windowFixed
    0.87
    oredCriteria
    0.85
     TestBed
    0.84
     unknownFields
    0.82
    IsMutable
    0.79
    MigrationBuilder
    0.79
    setupUi
    0.79
    UnsafeEnabled
    0.78
    Activations Density 0.082%

    No Known Activations