© 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. 1-CLT-HP
    7. 11550
    Prev
    Next
    INDEX
    Explanations

    elling

    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
     jotka
    -0.44
    <bos>
    -0.41
    (
    -0.40
    N
    -0.40
     temporales
    -0.40
     který
    -0.39
    over
    -0.38
     sezione
    -0.37
     versões
    -0.37
    et
    -0.36
    POSITIVE LOGITS
     дописавши
    1.11
     defStyle
    0.84
    dymyr
    0.77
     ModelExpression
    0.75
    #
    0.73
    IDENTAL
    0.73
     Chy
    0.73
    dolu
    0.71
    /***/
    0.71
    Sucesor
    0.69
    Activations Density 0.054%

    No Known Activations