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. 1-CLT-HP
    4. 12809
    Prev
    Next
    INDEX
    Explanations

    crime or acting

    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
    IntoConstraints
    -0.75
    NgModule
    -0.72
     disulfide
    -0.69
    HomeAsUpEnabled
    -0.66
     reciprocity
    -0.63
     +=
    -0.61
    exion
    -0.61
    sizeCache
    -0.61
    RUnlock
    -0.60
     DBNull
    -0.60
    POSITIVE LOGITS
     للاسماء
    0.58
     Wikimedijinoj
    0.46
    iestety
    0.45
     misure
    0.43
    setRow
    0.42
     insectes
    0.41
     generales
    0.41
     nascita
    0.41
     vasta
    0.41
     térm
    0.40
    Activations Density 0.024%

    No Known Activations