© 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. 5-CLT-HP
    7. 95000
    Prev
    Next
    INDEX
    Explanations

    comparisons and quantities

    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
     Administrativna
    -0.46
    +$
    -0.44
    ніципалі
    -0.44
    asString
    -0.43
    $
    -0.42
    bracht
    -0.42
     *$
    -0.41
    farwyddwr
    -0.41
     favoris
    -0.40
     Blatt
    -0.40
    POSITIVE LOGITS
     CreateTagHelper
    0.77
     AssemblyCulture
    0.74
    VersionUID
    0.68
    RunWith
    0.63
     geograph
    0.62
    GEBURTSDATUM
    0.61
     airports
    0.60
    CompleteListener
    0.60
     nurseries
    0.59
     beaches
    0.57
    Activations Density 0.002%

    No Known Activations