© 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. 1-CLT-HP
    7. 10407
    Prev
    Next
    INDEX
    Explanations

    salt

    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
     salt
    -1.45
    salt
    -1.40
     Salt
    -1.25
    Salt
    -1.13
     SALT
    -0.79
    sal
    -0.75
    SALT
    -0.73
    盐
    -0.71
     salts
    -0.68
    鹽
    -0.63
    POSITIVE LOGITS
     doubtnut
    0.68
     whoſe
    0.61
     Mev
    0.59
     дописавши
    0.59
     piaggio
    0.58
     quæ
    0.57
     للاسماء
    0.56
     Jefus
    0.56
     itſelf
    0.55
     Masonry
    0.54
    Activations Density 0.281%

    No Known Activations