© 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. 305
    Prev
    Next
    INDEX
    Explanations

    physical

    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
    Portale
    -0.71
     indisponible
    -0.69
     PHYSICAL
    -0.68
     physically
    -0.66
     Physical
    -0.66
     Мексичка
    -0.65
    Physical
    -0.64
    帖最后由
    -0.62
     physical
    -0.62
     poffible
    -0.61
    POSITIVE LOGITS
    ValueStyle
    0.70
    jooq
    0.54
     modeller
    0.50
    ModelBuilder
    0.47
     henvisninger
    0.46
     property
    0.46
     wizards
    0.46
    sor
    0.45
     model
    0.44
     properties
    0.44
    Activations Density 0.079%

    No Known Activations