© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 39938
    Prev
    Next
    INDEX
    Explanations

    Law

    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
    crest
    -0.64
     Crest
    -0.63
    lotl
    -0.56
     favor
    -0.55
    hassee
    -0.55
    Crest
    -0.54
     ARE
    -0.53
     McCall
    -0.52
    nament
    -0.52
    vatar
    -0.49
    POSITIVE LOGITS
     indépend
    0.73
     AssemblyVersion
    0.67
     HttpNotFound
    0.63
     lèvres
    0.61
     indépendante
    0.60
     surla
    0.59
     виправивши
    0.57
     bolsillos
    0.57
     anpass
    0.57
     ***!
    0.56
    Activations Density 0.465%

    No Known Activations