© 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. 4-CLT-HP
    7. 399
    Prev
    Next
    INDEX
    Explanations

    able

    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
     виправивши
    -0.90
    Personensuche
    -0.73
     تانيه
    -0.72
     avoient
    -0.69
     itſelf
    -0.68
     Theſe
    -0.67
     chré
    -0.67
     חיצוניים
    -0.66
     juges
    -0.65
     raiſ
    -0.65
    POSITIVE LOGITS
    peicher
    0.52
     the
    0.52
     major
    0.50
     implications
    0.49
     fruit
    0.48
    ê
    0.48
     konsek
    0.48
     how
    0.47
     direct
    0.47
     basic
    0.47
    Activations Density 0.005%

    No Known Activations