© 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. 1-CLT-HP
    7. 12292
    Prev
    Next
    INDEX
    Explanations

    achieve

    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
     pareti
    -0.54
    AddTagHelper
    -0.53
     Democrá
    -0.52
    Assad
    -0.50
    bearer
    -0.46
     État
    -0.44
    bearing
    -0.43
    FormTagHelper
    -0.43
    質
    -0.42
    modèle
    -0.42
    POSITIVE LOGITS
     تضيفلها
    0.82
    poptotic
    0.64
     cerebro
    0.63
     bone
    0.63
     coronary
    0.61
     peritoneal
    0.59
    DockStyle
    0.59
     blood
    0.58
    Carcinogenicity
    0.58
    istoitu
    0.57
    Activations Density 0.041%

    No Known Activations