© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43527
    Prev
    Next
    INDEX
    Explanations

    statistics

    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
     statistics
    -2.34
     Statistics
    -2.02
    Statistics
    -1.95
    statistics
    -1.83
     stats
    -1.79
     STATISTICS
    -1.78
     statistic
    -1.72
     Stats
    -1.64
     Statistic
    -1.51
     estadísticas
    -1.48
    POSITIVE LOGITS
    .
    0.64
    ⓧ
    0.63
    ,
    0.57
     of
    0.57
     that
    0.57
    override
    0.54
     for
    0.53
    Voltar
    0.51
     from
    0.49
     and
    0.48
    Activations Density 0.246%

    No Known Activations