© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77964
    Prev
    Next
    INDEX
    Explanations

    's' or 'a' words

    np_max-act-logits · 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
    KommentareTeilen
    -0.84
    IVEREF
    -0.81
    Демографія
    -0.75
    copg
    -0.70
    protoimpl
    -0.69
    NTIS
    -0.62
    MigrationBuilder
    -0.60
    ReusableCell
    -0.59
    Xna
    -0.57
    tagHelperRunner
    -0.57
    POSITIVE LOGITS
     such
    0.54
     Assume
    0.49
    Imagine
    0.48
    reciated
    0.48
    Assume
    0.47
     assume
    0.47
     sar
    0.45
    ipient
    0.45
    ndar
    0.44
     surely
    0.44
    Activations Density 0.000%

    No Known Activations