© 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. 45043
    Prev
    Next
    INDEX
    Explanations

    agine

    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
    agine
    -1.38
    atize
    -1.34
    hésite
    -0.63
    OrBuilder
    -0.59
    出版年
    -0.59
    Tikang
    -0.58
    jetivos
    -0.57
    hilangan
    -0.56
    ...";
    -0.54
    ifolium
    -0.54
    POSITIVE LOGITS
    Geplaatst
    0.80
    expandindo
    0.67
    +#+#
    0.56
    Extinguishing
    0.56
    GEBURTSDATUM
    0.54
    تقاوى
    0.54
    principalColumn
    0.54
     ums
    0.53
    GenerationType
    0.52
    ագրություններ
    0.51
    Activations Density 1.320%

    No Known Activations