© 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. 4599
    Prev
    Next
    INDEX
    Explanations

    names

    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
    __':
    -0.69
    GEBURTSDATUM
    -0.68
    ftagPool
    -0.66
     архивлан
    -0.61
    PreferredItem
    -0.61
    __":
    -0.57
    Geplaatst
    -0.56
    NewUrlParser
    -0.55
     {?}
    -0.54
    Становништво
    -0.54
    POSITIVE LOGITS
    InSection
    0.47
    databinding
    0.47
     travelling
    0.46
    ganet
    0.42
    UCKY
    0.42
    shire
    0.42
     travels
    0.42
    Chars
    0.42
     Missouri
    0.40
    umpul
    0.40
    Activations Density 0.001%

    No Known Activations