© 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. 20163
    Prev
    Next
    INDEX
    Explanations

    the word "bit" indicating a slight change or degree

    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
    Personensuche
    -0.85
    UrlResolution
    -0.76
    Seeder
    -0.75
    CloseOperation
    -0.73
     pleaſure
    -0.72
     Commencez
    -0.72
    DockStyle
    -0.71
    UseVisualStyle
    -0.71
    WriteAttribute
    -0.70
     ſmall
    -0.69
    POSITIVE LOGITS
     too
    0.76
     of
    0.63
    stuk
    0.61
    too
    0.60
     more
    0.60
    TOO
    0.58
     alapján
    0.58
     Jazeera
    0.57
     soumis
    0.56
     conduct
    0.56
    Activations Density 0.011%

    No Known Activations