© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14003
    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
    -0.86
     nahilalakip
    -0.75
     salt
    -0.71
     Salts
    -0.69
     Saline
    -0.68
    Salt
    -0.66
    例文帳に追加
    -0.61
    TintMode
    -0.60
    IsMutable
    -0.56
    Története
    -0.56
    POSITIVE LOGITS
    twimg
    0.49
    Viitteet
    0.49
    face
    0.48
    Suerte
    0.47
    wear
    0.47
    gem
    0.46
    head
    0.46
    Jereo
    0.46
    fall
    0.46
     ContentValues
    0.46
    Activations Density 0.006%

    No Known Activations