© 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. 2036
    Prev
    Next
    INDEX
    Explanations

    research reviews

    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
    rü
    -0.43
    du
    -0.42
    at
    -0.40
     vọng
    -0.40
    tel
    -0.39
    ant
    -0.38
    post
    -0.37
     uova
    -0.37
     felizes
    -0.37
    man
    -0.36
    POSITIVE LOGITS
    StructEnd
    0.85
    Aholisi
    0.77
    saraba
    0.73
     Мексичка
    0.73
    )];
    0.71
    bootstrapcdn
    0.70
    CloseOperation
    0.68
    AddAttribute
    0.68
     الاطلاع
    0.68
    BASEPATH
    0.67
    Activations Density 0.001%

    No Known Activations