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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 20
    Prev
    Next
    INDEX
    Explanations

    crisis

    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
    ✨:
    -0.71
     Efq
    -0.65
    Crisis
    -0.62
    WebVitals
    -0.59
    crisis
    -0.58
    ostante
    -0.58
    nefs
    -0.58
    theless
    -0.57
    antaranya
    -0.57
    IVEREF
    -0.57
    POSITIVE LOGITS
     of
    0.68
    BorderFactory
    0.50
     Fund
    0.44
    帖最后由
    0.44
    Fund
    0.44
    ็จ
    0.43
    eat
    0.43
    a
    0.42
     triggered
    0.42
    سجيل
    0.41
    Activations Density 0.107%

    No Known Activations