Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74442
    Prev
    Next
    INDEX
    Explanations

    technical/scientific texts

    np_max-act-logits · 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
    SequentialGroup
    -0.82
    createCanvas
    -0.68
    AnchorStyles
    -0.62
    URLException
    -0.59
    posedge
    -0.55
    addCriterion
    -0.54
     beginnetje
    -0.52
    expiresIn
    -0.51
     bezeichneter
    -0.51
    didSet
    -0.50
    POSITIVE LOGITS
    moz
    0.56
     الرياضيه
    0.55
     soort
    0.49
     XXXIII
    0.48
     privadas
    0.48
     Zacks
    0.47
    p
    0.47
     Polskiego
    0.46
     privada
    0.46
     mess
    0.46
    Activations Density 0.007%

    No Known Activations