© 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. 1-CLT-HP
    7. 45732
    Prev
    Next
    INDEX
    Explanations

    fix

    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
     marquées
    -0.69
    väg
    -0.63
     traditionnels
    -0.60
     positifs
    -0.59
     scatola
    -0.58
     lèvres
    -0.58
     boî
    -0.58
     extérieures
    -0.57
    mphony
    -0.56
     jäsen
    -0.56
    POSITIVE LOGITS
    __((
    0.64
    évaluateur
    0.63
     disambiguazione
    0.60
    "])
    0.60
    Referències
    0.60
    TypedDataSet
    0.55
    prüche
    0.55
    }])
    0.55
    RectangleBorder
    0.54
    sizeCache
    0.54
    Activations Density 0.027%

    No Known Activations