© 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. 95103
    Prev
    Next
    INDEX
    Explanations

    programming/math/science

    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
    #!/
    -0.56
     ferons
    -0.52
     nakalista
    -0.51
     soldati
    -0.50
     Biôgrafia
    -0.46
    GenerationType
    -0.45
    Padding
    -0.45
     göre
    -0.44
     prieš
    -0.44
    CGRectMake
    -0.43
    POSITIVE LOGITS
    rrggbb
    0.62
    elemField
    0.59
    rmtree
    0.57
    iciens
    0.56
    MethodManager
    0.55
    tanleria
    0.55
    parsedMessage
    0.55
    __);
    0.55
     Numerade
    0.54
    RuleContext
    0.54
    Activations Density 0.004%

    No Known Activations