© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91210
    Prev
    Next
    INDEX
    Explanations

    plan

    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
     plan
    -1.77
     plans
    -1.37
     Plan
    -1.36
    plan
    -1.36
    Plan
    -1.21
     PLAN
    -1.20
     planning
    -1.12
     Plans
    -1.06
    plans
    -1.05
     planned
    -0.99
    POSITIVE LOGITS
    InjectAttribute
    0.88
    tagext
    0.85
     незавершена
    0.85
    EDEFAULT
    0.85
    RTLD
    0.84
    addCriterion
    0.84
    featureID
    0.79
    Jeografia
    0.78
    richTextPanel
    0.76
    таратура
    0.76
    Activations Density 0.064%

    No Known Activations