© 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. 4779
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     مرئيه
    -0.54
    InjectAttribute
    -0.50
    DebuggerNonUser
    -0.48
    Closure
    -0.47
    zość
    -0.46
     Ammon
    -0.46
     ?',
    -0.45
    elding
    -0.44
     Closure
    -0.44
    ifer
    -0.43
    POSITIVE LOGITS
    ConstraintMaker
    0.76
    StoryboardSegue
    0.62
    IntoConstraints
    0.58
    netic
    0.54
     unknownFields
    0.52
    migrationBuilder
    0.51
    ometri
    0.51
    ResumeLayout
    0.51
     للاسماء
    0.50
    Statistiche
    0.50
    Activations Density 0.000%

    No Known Activations