Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16298
    Prev
    Next
    INDEX
    Explanations

    phrases related to having a difficult time navigating strong emotions.

    oai_token-act-pair · gemini-2.0-flash

    Negative experiences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BufferException
    -0.66
    حياته
    -0.60
    wikidata
    -0.57
    ">//
    -0.57
     متعلقه
    -0.56
    InstanceState
    -0.55
    ,‎
    -0.54
    gep
    -0.53
    ReusableCell
    -0.53
    VersionUID
    -0.53
    POSITIVE LOGITS
    argout
    0.53
    mittags
    0.53
    localctx
    0.50
    Obrázky
    0.50
    $_['
    0.47
    posição
    0.47
    thers
    0.47
    égration
    0.46
    OPTIONS
    0.46
    urope
    0.45
    Activations Density 0.786%

    No Known Activations