© 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. 43993
    Prev
    Next
    INDEX
    Explanations

    optic

    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
     mágica
    -0.88
     mágico
    -0.76
     magique
    -0.76
     eût
    -0.75
     battre
    -0.75
     magnétique
    -0.75
     magnético
    -0.73
    magic
    -0.72
     réjou
    -0.70
     démocr
    -0.69
    POSITIVE LOGITS
    ly
    0.71
     OFDb
    0.70
    ities
    0.59
    ser
    0.58
    twimg
    0.56
    ConstraintMaker
    0.55
    son
    0.54
    spro
    0.54
    idad
    0.53
    mos
    0.52
    Activations Density 0.270%

    No Known Activations