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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41108
    Prev
    Next
    INDEX
    Explanations

    applies

    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
     resourceCulture
    -0.90
    principalTable
    -0.88
    tagext
    -0.88
     Efq
    -0.83
     Jefus
    -0.81
    脚注の使い方
    -0.80
    Personensuche
    -0.78
     poffible
    -0.78
     himſelf
    -0.78
    adaptiveStyles
    -0.77
    POSITIVE LOGITS
    ה
    0.49
     fuer
    0.48
     il
    0.46
    ^^^^^^^^
    0.45
    ány
    0.45
    сь
    0.44
     ش
    0.42
    zó
    0.42
    Xi
    0.41
     Il
    0.41
    Activations Density 0.073%

    No Known Activations