© 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
    2. Gemma-2-2B
    3. 24-RES-MATRYOSHKA-DC
    4. 824
    Prev
    Next
    INDEX
    Explanations

    articles, possessive pronouns, superlatives, small numbers, and some team names in the context of sports analysis

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
     atve
    -0.54
     resourceCulture
    -0.52
    nofollow
    -0.49
    complexContent
    -0.46
    orra
    -0.46
    Matched
    -0.45
     Welt
    -0.44
    könig
    -0.44
    jogador
    -0.44
     vectorielles
    -0.43
    POSITIVE LOGITS
    tonode
    0.68
     team
    0.63
    ועל
    0.62
     Soon
    0.60
    ArrowToggle
    0.59
     <>",
    0.59
     visitors
    0.57
    AutoresizingMask
    0.57
    帖最后由
    0.57
     Volunteers
    0.55
    Activations Density 0.423%

    No Known Activations