© 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. 4388
    Prev
    Next
    INDEX
    Explanations

    director

    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
     telehealth
    -0.52
    IntoConstraints
    -0.49
    脚注の使い方
    -0.47
    Obrázky
    -0.47
    getTag
    -0.46
     tele
    -0.45
     habari
    -0.44
     DbType
    -0.43
    <#
    -0.43
    Gears
    -0.42
    POSITIVE LOGITS
    Portail
    0.67
    rungsseite
    0.65
    AutoField
    0.62
    WebControls
    0.59
    awaiter
    0.58
    verwijspagina
    0.56
    expandindo
    0.55
    antMatchers
    0.54
    databind
    0.53
    isa
    0.52
    Activations Density 0.002%

    No Known Activations