© 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. 3793
    Prev
    Next
    INDEX
    Explanations

    causes

    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
    ĝis
    -0.45
     Drapeau
    -0.41
    kor
    -0.40
    anais
    -0.40
     resalt
    -0.39
     nakalista
    -0.37
     Tactics
    -0.36
     Jacket
    -0.36
    zystać
    -0.35
    their
    -0.35
    POSITIVE LOGITS
     beginnetje
    0.84
    LookAnd
    0.82
     NSCoder
    0.77
     pleaſure
    0.77
    MigrationBuilder
    0.77
     Efq
    0.76
     purpoſe
    0.75
     Majefty
    0.75
     itſelf
    0.73
     initComponents
    0.72
    Activations Density 0.010%

    No Known Activations