© 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. 0-CLT-HP
    7. 43235
    Prev
    Next
    INDEX
    Explanations

    groups/components

    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
    LookAnd
    -0.90
    TintMode
    -0.84
     nakalista
    -0.74
    таратура
    -0.73
     تضيفلها
    -0.71
    RTEX
    -0.71
    expandindo
    -0.70
    <bos>
    -0.68
     للاسماء
    -0.66
     propOrder
    -0.63
    POSITIVE LOGITS
     Theoretical
    0.50
     OnClickListener
    0.49
     createSlice
    0.47
    etsch
    0.46
     Machine
    0.46
     logits
    0.44
     lask
    0.44
    estinal
    0.44
     theoretical
    0.43
     Manufacturing
    0.43
    Activations Density 0.074%

    No Known Activations