© 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. 4461
    Prev
    Next
    INDEX
    Explanations

    separation

    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
     each
    -0.81
     individual
    -0.70
    NameInMap
    -0.68
    MigrationBuilder
    -0.64
    Each
    -0.63
    EACH
    -0.62
     separate
    -0.62
     từng
    -0.62
    ggable
    -0.61
     defaultstate
    -0.61
    POSITIVE LOGITS
    ########.
    0.62
     to
    0.56
    .
    0.54
    ,
    0.49
     Trains
    0.49
     trasero
    0.47
    mybatisplus
    0.46
     dianteiro
    0.44
    Дереккөздер
    0.44
     verdad
    0.43
    Activations Density 0.001%

    No Known Activations