© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3687
    Prev
    Next
    INDEX
    Explanations

    code

    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
    󠁢
    -0.83
    ResumeLayout
    -0.70
    ActionCreators
    -0.62
    shades
    -0.61
    tableFuture
    -0.60
     Filling
    -0.59
    IsPostBack
    -0.58
    AxisAlignment
    -0.58
     Buttons
    -0.57
     Offisielt
    -0.57
    POSITIVE LOGITS
     ten
    0.38
    Ten
    0.36
     bid
    0.36
     gyhoeddwyd
    0.35
     IR
    0.35
     Ten
    0.35
    inoma
    0.35
     Decade
    0.35
    Искәрмәләр
    0.35
    üb
    0.34
    Activations Density 0.017%

    No Known Activations