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. 20-CLT-HP
    4. 74236
    Prev
    Next
    INDEX
    Explanations

    Syllables

    np_max-act-logits · 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
     تضيفلها
    -0.88
    Personensuche
    -0.78
     PublicKey
    -0.77
    DockStyle
    -0.75
    xase
    -0.74
    adaptiveStyles
    -0.73
    ⓧ
    -0.73
    出版年
    -0.72
    脚注の使い方
    -0.71
     كومونز
    -0.71
    POSITIVE LOGITS
    ne
    0.51
     all
    0.42
     sli
    0.40
    all
    0.40
    3
    0.39
     paid
    0.38
    9
    0.38
    $
    0.38
    τε
    0.36
    me
    0.35
    Activations Density 0.001%

    No Known Activations