© 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. 13050
    Prev
    Next
    INDEX
    Explanations

    group

    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
    onAttach
    -0.62
     صوتيه
    -0.61
     الحره
    -0.59
    Tazama
    -0.57
     viagem
    -0.54
    لينكات
    -0.54
    loyer
    -0.53
     bezeichneter
    -0.53
     saudável
    -0.53
     uVar
    -0.53
    POSITIVE LOGITS
     ate
    0.54
     chocolate
    0.53
     molasses
    0.49
     Chocolate
    0.49
    省市镇
    0.49
     succeeding
    0.48
    optionalTypeArgs
    0.47
     guaranteeing
    0.45
     giving
    0.44
     consequ
    0.44
    Activations Density 0.015%

    No Known Activations