© 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. 92136
    Prev
    Next
    INDEX
    Explanations

    sells

    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
     participates
    -0.41
    ädie
    -0.40
     كومونز
    -0.38
     exemplos
    -0.36
     particulares
    -0.36
    Begriffsklä
    -0.35
     infatti
    -0.34
     therefore
    -0.33
    zwald
    -0.33
     participating
    -0.33
    POSITIVE LOGITS
    sizeCache
    0.91
    EndGlobalSection
    0.79
    Portale
    0.68
    createCanvas
    0.66
    Portail
    0.66
    indicato
    0.65
    <bos>
    0.64
     néglig
    0.64
    المكان
    0.64
    LookAnd
    0.63
    Activations Density 0.004%

    No Known Activations