© 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. 5282
    Prev
    Next
    INDEX
    Explanations

    me

    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
    <bos>
    -0.54
     juga
    -0.49
     sẻ
    -0.47
     also
    -0.46
     päivä
    -0.44
     vidare
    -0.44
     als
    -0.43
     pedra
    -0.43
    ///
    -0.43
     al
    -0.41
    POSITIVE LOGITS
    ReusableCell
    0.88
    RenderAtEndOf
    0.87
    parsedMessage
    0.79
     оригіналу
    0.78
     onOptions
    0.76
     NSCoder
    0.75
    CloseOperation
    0.75
    LookAnd
    0.71
    Portale
    0.69
     الرياضيه
    0.68
    Activations Density 0.001%

    No Known Activations