© 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. 98012
    Prev
    Next
    INDEX
    Explanations

    types of writings

    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
    PreferredItem
    -0.69
    AndEndTag
    -0.67
    تقاوى
    -0.67
    WebElementEntity
    -0.65
     beginnetje
    -0.65
     wireType
    -0.65
     دیکھیے
    -0.63
     NDEBUG
    -0.63
     היתה
    -0.63
     was
    -0.62
    POSITIVE LOGITS
     alatt
    0.47
     alá
    0.46
    styleable
    0.46
     And
    0.45
    صه
    0.43
    ViewById
    0.41
    And
    0.41
    Sad
    0.41
    anmoins
    0.40
     rues
    0.40
    Activations Density 0.001%

    No Known Activations