© 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. 1-CLT-HP
    7. 45822
    Prev
    Next
    INDEX
    Explanations

    descriptions and recollections

    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
    oly
    -0.58
    ax
    -0.56
    brä
    -0.55
     Référence
    -0.53
    ry
    -0.52
    дон
    -0.51
    sie
    -0.50
    oo
    -0.50
    eaker
    -0.50
    @
    -0.50
    POSITIVE LOGITS
    oredCriteria
    0.74
    RenderAtEndOf
    0.73
    談社
    0.66
    IsContent
    0.66
    StructEnd
    0.62
    bandcamp
    0.62
    Personendaten
    0.59
    principalTable
    0.58
    ésult
    0.58
    SafeMath
    0.58
    Activations Density 0.097%

    No Known Activations