© 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. 97497
    Prev
    Next
    INDEX
    Explanations

    ним

    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
     cô
    -0.52
     Réponses
    -0.51
    ↵
    -0.48
    InjectAttribute
    -0.47
     é
    -0.47
     informée
    -0.46
    creativecommons
    -0.45
    oleum
    -0.45
     Chwiliwch
    -0.45
    ween
    -0.44
    POSITIVE LOGITS
     endwhile
    0.74
    󠁣
    0.68
     paddles
    0.66
    saraba
    0.64
     poffe
    0.63
     barbati
    0.60
     cór
    0.59
     quirúrg
    0.59
     brancas
    0.58
    CreateModel
    0.57
    Activations Density 1.716%

    No Known Activations