© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 98063
    Prev
    Next
    INDEX
    Explanations

    start of phrases

    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
    StructEnd
    -0.88
    OGND
    -0.84
     NSCoder
    -0.80
     gynhyrchwyd
    -0.78
    Geplaatst
    -0.77
     Roskov
    -0.74
    ThroughAttribute
    -0.73
    HtmlAttribute
    -0.72
    Autoritní
    -0.72
    LookAnd
    -0.68
    POSITIVE LOGITS
     any
    0.55
     even
    0.54
     anything
    0.54
     Place
    0.46
     of
    0.46
    ोंने
    0.46
    priate
    0.44
     really
    0.44
     caused
    0.43
     cause
    0.42
    Activations Density 0.002%

    No Known Activations