© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 95109
    Prev
    Next
    INDEX
    Explanations

    blog excerpts

    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
     nieco
    -0.51
     cependant
    -0.49
     gewisser
    -0.48
     Etwas
    -0.48
     trochę
    -0.48
    opsida
    -0.46
    However
    -0.46
     somewhat
    -0.45
    有点
    -0.45
     entanto
    -0.45
    POSITIVE LOGITS
    IndentedString
    0.68
    VersionUID
    0.66
    PostExecute
    0.63
    GraphicsUnit
    0.61
     незавершена
    0.61
     AttributeSet
    0.61
    DockStyle
    0.60
     للمعارف
    0.59
     chi̍t
    0.59
     either
    0.58
    Activations Density 0.011%

    No Known Activations