© 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. 1-CLT-HP
    7. 384
    Prev
    Next
    INDEX
    Explanations

    angi

    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
    دانشنامهٔ
    -0.69
    msgTypes
    -0.61
     <=",
    -0.60
     ++)
    -0.57
     entretien
    -0.54
    áp
    -0.54
     चीज़ों
    -0.54
    "},
    -0.53
    ibility
    -0.52
    PreferredItem
    -0.52
    POSITIVE LOGITS
     تضيفلها
    0.59
     كمان
    0.54
    exels
    0.52
    raux
    0.50
    ském
    0.48
    AndEndTag
    0.46
    ով
    0.46
    e
    0.45
     OkHttpClient
    0.45
     Secondo
    0.45
    Activations Density 0.048%

    No Known Activations