© 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. 4-CLT-HP
    7. 4431
    Prev
    Next
    INDEX
    Explanations

    visual context/references

    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
     <=",
    -0.69
    AddHtmlAttribute
    -0.68
    ="#"><
    -0.59
    <![
    -0.57
    dAtA
    -0.57
     BoxFit
    -0.57
    RetentionPolicy
    -0.57
    enumii
    -0.55
    StructEnd
    -0.54
     noqa
    -0.53
    POSITIVE LOGITS
     Administrativna
    0.57
     disambiguazione
    0.52
    them
    0.50
     femininas
    0.47
     dignité
    0.47
    Pointers
    0.47
    leby
    0.47
    amssymb
    0.45
    ulitis
    0.44
    acceso
    0.42
    Activations Density 0.001%

    No Known Activations