© 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. 5-CLT-HP
    7. 96906
    Prev
    Next
    INDEX
    Explanations

    a

    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
     }{@
    -0.50
    only
    -0.47
    word
    -0.46
    Scaler
    -0.46
    way
    -0.46
    ie
    -0.45
    وانید
    -0.44
     ngờ
    -0.44
    don
    -0.44
    uding
    -0.43
    POSITIVE LOGITS
     fact
    0.67
    endphp
    0.64
    PreExecute
    0.63
    bcryptjs
    0.59
     benefit
    0.59
     IBOutlet
    0.59
     feature
    0.59
     sign
    0.59
    ratulations
    0.59
     result
    0.58
    Activations Density 0.000%

    No Known Activations