© 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. 1264
    Prev
    Next
    INDEX
    Explanations

    ropic

    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
     Efq
    -0.96
     Theſe
    -0.96
     Majefty
    -0.92
     themſelves
    -0.91
     fubject
    -0.86
     myſelf
    -0.85
     Jefus
    -0.85
     poffe
    -0.82
     Reſ
    -0.82
     itſelf
    -0.82
    POSITIVE LOGITS
    HtmlAttribute
    0.63
     of
    0.62
    луй
    0.59
    BeforeAll
    0.57
     استنادى
    0.54
    httphttps
    0.53
    許
    0.52
     оригіналу
    0.51
    .
    0.51
     ويكيميديا
    0.48
    Activations Density 0.117%

    No Known Activations