© 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. 1-CLT-HP
    7. 9829
    Prev
    Next
    INDEX
    Explanations

    surveys

    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
    mybatisplus
    -0.78
    MigrationBuilder
    -0.68
    AndEndTag
    -0.66
    Cyfeiriadau
    -0.66
    Personendaten
    -0.63
     shave
    -0.59
    ftagPool
    -0.59
     незавершена
    -0.56
     Signalez
    -0.55
    OGND
    -0.55
    POSITIVE LOGITS
    ivka
    0.56
    itans
    0.52
    inio
    0.49
    chak
    0.48
    fiddle
    0.47
    geschlossen
    0.47
    cest
    0.44
    čen
    0.44
    قدام
    0.43
    タジー
    0.43
    Activations Density 0.020%

    No Known Activations