© 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. 4-CLT-HP
    7. 4361
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     '{@
    -0.72
    GraphicsUnit
    -0.69
    GEBURTSDATUM
    -0.65
    oredCriteria
    -0.65
    DockStyle
    -0.62
    RenderAtEndOf
    -0.60
     CGRectMake
    -0.58
    TypedDataSet
    -0.57
     QName
    -0.57
     EconPapers
    -0.56
    POSITIVE LOGITS
    paravant
    0.51
     cụ
    0.45
    ufort
    0.44
    s
    0.44
    inquirer
    0.43
    sa
    0.43
    kaido
    0.42
    .
    0.42
    slideUp
    0.40
     niem
    0.39
    Activations Density 0.001%

    No Known Activations