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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 171
    Prev
    Next
    INDEX
    Explanations

    image captions

    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
     caption
    -0.72
     captions
    -0.69
     Caption
    -0.60
    Caption
    -0.59
    caption
    -0.59
     Captions
    -0.56
     captioned
    -0.54
    CAPTION
    -0.54
     kasarigan
    -0.53
     h
    -0.52
    POSITIVE LOGITS
    ThroughAttribute
    0.76
     becauſe
    0.73
     myſelf
    0.72
     purpoſe
    0.71
     itſelf
    0.71
    TargetException
    0.71
    ✨:
    0.70
     économies
    0.67
     illustrazione
    0.67
     Efq
    0.67
    Activations Density 0.004%

    No Known Activations