© 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. 5-CLT-HP
    7. 93118
    Prev
    Next
    INDEX
    Explanations

    the

    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
     nor
    -1.12
    nor
    -0.93
     sondern
    -0.86
     melainkan
    -0.83
    Nor
    -0.81
     Nor
    -0.76
     بلکه
    -0.74
     neither
    -0.73
    而是
    -0.68
     Neither
    -0.68
    POSITIVE LOGITS
    StoreMessageInfo
    0.59
     ويكيميديا
    0.55
    keywords
    0.49
     defaultstate
    0.49
    uteen
    0.48
    Configurer
    0.46
    ⎨
    0.46
    脚注の使い方
    0.46
     Censo
    0.46
    κης
    0.46
    Activations Density 0.011%

    No Known Activations