© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1997
    Prev
    Next
    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.59
     he
    -0.51
    彼は
    -0.42
    ’
    -0.41
    timb
    -0.41
     anunciou
    -0.38
     she
    -0.38
     himself
    -0.38
     bVar
    -0.38
     seemed
    -0.37
    POSITIVE LOGITS
     Roskov
    0.87
    DockStyle
    0.82
     ModelExpression
    0.81
    сылкі
    0.76
    HomeAsUpEnabled
    0.73
     ProtoMessage
    0.71
    ClientSize
    0.68
    ніципа
    0.68
     protoimpl
    0.68
     Италијани
    0.68
    Activations Density 0.011%

    No Known Activations