© 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. 0-CLT-HP
    7. 44124
    Prev
    Next
    INDEX
    Explanations

    Phillips

    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
    GenerationType
    -0.68
     Hass
    -0.61
    istered
    -0.54
    ULATOR
    -0.54
    IBILITY
    -0.52
    RECOMMEND
    -0.52
    JsonHelper
    -0.52
    ounces
    -0.50
    omeness
    -0.50
    folded
    -0.49
    POSITIVE LOGITS
    findpost
    0.79
    AddTagHelper
    0.76
     صوتيه
    0.73
     ThemeData
    0.69
     estekak
    0.67
     protoimpl
    0.67
    httphttps
    0.67
    buttonShape
    0.67
     ویکی‌پدیا
    0.66
    تقاوى
    0.66
    Activations Density 1.298%

    No Known Activations