© 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. 1234
    Prev
    Next
    INDEX
    Explanations

    Comparisons and descriptions

    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
     steeper
    -0.84
     thicker
    -0.72
    adaptiveStyles
    -0.71
     taller
    -0.59
     faptul
    -0.59
     tweezers
    -0.59
     hotter
    -0.58
    potent
    -0.58
     aggiun
    -0.56
     habet
    -0.56
    POSITIVE LOGITS
    Xna
    0.56
     disasters
    0.49
    SUZ
    0.49
    OnAdd
    0.48
    Obras
    0.47
    ikos
    0.47
    cover
    0.47
    rxjs
    0.47
     sie
    0.47
     than
    0.46
    Activations Density 0.281%

    No Known Activations