Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12658
    Prev
    Next
    INDEX
    Explanations

    research studies

    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
    tamol
    -0.76
    تفصیلات
    -0.69
    utilisons
    -0.69
    achios
    -0.65
    mployment
    -0.62
    kuuta
    -0.62
     Gop
    -0.60
    уда
    -0.60
    Autoritní
    -0.60
    #+#
    -0.60
    POSITIVE LOGITS
     indig
    0.44
    ワイイ
    0.43
    Sucesor
    0.41
    '>";
    0.41
     समीक्षाओं
    0.41
     widest
    0.40
    rids
    0.40
    اخت
    0.39
     farlo
    0.39
    ⓧ
    0.39
    Activations Density 0.019%

    No Known Activations