© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93810
    Prev
    Next
    INDEX
    Explanations

    Ok

    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
    di
    -0.56
     di
    -0.55
     A
    -0.54
     the
    -0.52
     in
    -0.52
     South
    -0.51
     a
    -0.50
    son
    -0.48
     report
    -0.48
    ing
    -0.47
    POSITIVE LOGITS
    ✨:
    0.80
    featureID
    0.68
     BoxFit
    0.68
    脚注の使い方
    0.67
    ^(@)
    0.66
     Theſe
    0.66
     PLWABN
    0.64
    XMLSchema
    0.64
     تانيه
    0.64
    AndEndTag
    0.63
    Activations Density 0.016%

    No Known Activations