© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1593
    Prev
    Next
    INDEX
    Explanations

    eye

    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
     eye
    -2.42
     Eye
    -1.96
    eye
    -1.81
    Eye
    -1.81
     EYE
    -1.76
    EYE
    -1.56
     ey
    -1.43
     Ey
    -1.16
    Eyed
    -1.15
    Ey
    -1.13
    POSITIVE LOGITS
    block
    0.65
    UnusedPrivate
    0.61
    let
    0.57
    windowFixed
    0.57
    AutoScaleMode
    0.56
    GrantedAuthority
    0.55
     Geraadpleegd
    0.55
     للاسماء
    0.53
    break
    0.52
    tip
    0.52
    Activations Density 0.107%

    No Known Activations