© 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. 1-CLT-HP
    7. 15713
    Prev
    Next
    INDEX
    Explanations

    toxic or harmful

    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
    /***/
    -0.52
    itzende
    -0.49
     AspNetCore
    -0.48
    matchCondition
    -0.48
    voix
    -0.47
     Dimension
    -0.47
    逅
    -0.46
     Landwir
    -0.46
    aarrggbb
    -0.46
    eled
    -0.45
    POSITIVE LOGITS
    Personendaten
    0.67
    Билгалдахарш
    0.65
    IsContent
    0.54
    Whole
    0.53
    Systematic
    0.52
    ifiz
    0.50
    ⓧ
    0.50
    щество
    0.49
     tutors
    0.49
    Kako
    0.49
    Activations Density 0.025%

    No Known Activations