© 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. 1047
    Prev
    Next
    INDEX
    Explanations

    damage

    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
    onOptions
    -0.71
     Italijanski
    -0.59
     Мексичка
    -0.52
    MockBean
    -0.52
    BlockPos
    -0.50
    annotation
    -0.50
     percolation
    -0.49
     strconv
    -0.49
    LLocation
    -0.49
     expressão
    -0.48
    POSITIVE LOGITS
     in
    0.66
     during
    0.66
     AssemblyCulture
    0.65
    webElementXpaths
    0.54
     en
    0.52
     sustained
    0.51
     incurred
    0.51
     from
    0.50
    DockStyle
    0.49
    षण
    0.49
    Activations Density 0.002%

    No Known Activations