© 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. 4-CLT-HP
    7. 2812
    Prev
    Next
    INDEX
    Explanations

    release

    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
     smut
    -0.68
    AttributeSet
    -0.67
     lexical
    -0.65
    ysl
    -0.65
     snuff
    -0.65
     ExecuteAsync
    -0.63
     coö
    -0.62
     Negroes
    -0.61
     disulfide
    -0.61
     subsoil
    -0.61
    POSITIVE LOGITS
    iastes
    0.46
     devenus
    0.46
    <bos>
    0.44
     medlem
    0.44
     joined
    0.43
    ↵
    0.41
     quitté
    0.41
    Identyfik
    0.39
    โม
    0.39
     fuente
    0.39
    Activations Density 0.019%

    No Known Activations