© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93247
    Prev
    Next
    INDEX
    Explanations

    demonstrations, orders, general topics

    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
    ValueStyle
    -1.05
    InjectAttribute
    -1.02
     cherchés
    -0.99
     nahilalakip
    -0.92
    RenderAtEndOf
    -0.84
    ScopeManager
    -0.83
    enderror
    -0.83
     nonUne
    -0.83
    ✨:
    -0.81
     للاسماء
    -0.79
    POSITIVE LOGITS
     best
    0.46
     n
    0.44
     Best
    0.43
     and
    0.42
    ectos
    0.42
    ::::::::
    0.40
     to
    0.40
     on
    0.40
     apply
    0.39
     provision
    0.38
    Activations Density 0.046%

    No Known Activations