© 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. 6-RES-MATRYOSHKA-DC
    7. 372
    Prev
    Next
    INDEX
    Explanations

    the word "not" and contractions that include 't'

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hammer
    -0.78
     aucune
    -0.74
     no
    -0.71
    无
    -0.67
     alcuna
    -0.64
    addListener
    -0.62
     Ibarra
    -0.62
    PII
    -0.62
     Hickman
    -0.62
    Thu
    -0.61
    POSITIVE LOGITS
    not
    1.19
    NOT
    1.14
     Not
    1.12
     NOT
    1.11
     not
    1.08
    Not
    1.08
     Normdatei
    0.93
    isNot
    0.91
    ConstraintMaker
    0.88
    sweise
    0.88
    Activations Density 1.440%

    No Known Activations