© 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. 92075
    Prev
    Next
    INDEX
    Explanations

    hemato

    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
    m
    -0.81
     defaultstate
    -0.81
    InjectAttribute
    -0.72
    l
    -0.68
    t
    -0.65
    b
    -0.65
    ValueStyle
    -0.63
    p
    -0.62
    y
    -0.62
    oa̍t
    -0.62
    POSITIVE LOGITS
    poietic
    0.60
    Czytaj
    0.54
     itſelf
    0.54
    pleft
    0.52
    ſelves
    0.51
     himſelf
    0.49
    pole
    0.48
    innocent
    0.47
     poffible
    0.47
     ſeveral
    0.47
    Activations Density 1.818%

    No Known Activations