© 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. 4843
    Prev
    Next
    INDEX
    Explanations

    hyphens

    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
     himself
    -0.47
    himself
    -0.44
    themselves
    -0.37
     видом
    -0.37
     】
    -0.37
    him
    -0.36
     вида
    -0.36
    Ú
    -0.36
    ("%.
    -0.36
    　　“
    -0.35
    POSITIVE LOGITS
    MigrationBuilder
    0.97
     للمعارف
    0.92
    setVerticalGroup
    0.89
    StoryboardSegue
    0.84
     '\\;'
    0.83
     متعلقه
    0.80
     thats
    0.79
     ModelExpression
    0.77
     its
    0.77
    DeleteBehavior
    0.76
    Activations Density 0.005%

    No Known Activations