© 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. 0-CLT-HP
    7. 42824
    Prev
    Next
    INDEX
    Explanations

    statistical studies/correlations

    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
    RetentionPolicy
    -0.88
     Common
    -0.59
    theless
    -0.59
     COMMON
    -0.59
    bbene
    -0.56
    e
    -0.56
     ARXIV
    -0.55
    yntaxException
    -0.54
    ed
    -0.53
    pler
    -0.52
    POSITIVE LOGITS
    AutoScaleMode
    0.70
    matchCondition
    0.57
    writeFieldEnd
    0.53
    dighet
    0.50
    Demografía
    0.49
    webElementXpaths
    0.49
    وفاته
    0.48
    itzen
    0.48
    twimg
    0.47
     strike
    0.47
    Activations Density 0.106%

    No Known Activations