© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91165
    Prev
    Next
    INDEX
    Explanations

    respectively

    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
    ɵɵ
    -0.41
     more
    -0.40
     a
    -0.39
     the
    -0.36
     ability
    -0.35
    бы
    -0.35
    le
    -0.35
     sty
    -0.35
    ENS
    -0.35
     state
    -0.34
    POSITIVE LOGITS
    GraphicsUnit
    1.00
     Efq
    0.88
     doubtnut
    0.87
     heureuse
    0.83
    tonode
    0.79
    tvguidetime
    0.77
    HasForeignKey
    0.77
    AutoScaleMode
    0.75
    SceneManagement
    0.74
    sidemargin
    0.73
    Activations Density 0.003%

    No Known Activations