© 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. 1962
    Prev
    Next
    INDEX
    Explanations

    module

    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
    stateParams
    -0.54
    Let
    -0.48
    verwijspagina
    -0.48
     réunions
    -0.48
    seiti
    -0.48
     Let
    -0.48
     recommandons
    -0.48
    seitige
    -0.47
     {}));
    -0.47
     inflater
    -0.47
    POSITIVE LOGITS
    esgue
    0.68
    RectangleBorder
    0.60
    styleable
    0.55
    TabLayout
    0.51
     Spir
    0.49
    abestanden
    0.49
    locaust
    0.48
     NSCoder
    0.48
    المناصب
    0.47
    сій
    0.47
    Activations Density 0.000%

    No Known Activations