© 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. 42544
    Prev
    Next
    INDEX
    Explanations

    Exactly

    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
     Exactly
    -0.68
    SerializedName
    -0.64
    t
    -0.63
    d
    -0.62
    ings
    -0.60
    ed
    -0.60
    Exactly
    -0.57
     validamos
    -0.57
    ness
    -0.56
    ink
    -0.56
    POSITIVE LOGITS
    mybatisplus
    0.64
     defaultstate
    0.63
     yawn
    0.62
    issory
    0.60
    /*---
    0.57
    tagext
    0.56
    rungsseite
    0.55
    ArrowToggle
    0.55
     perdita
    0.54
     éven
    0.54
    Activations Density 1.333%

    No Known Activations