© 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. 3-RES-MATRYOSHKA-DC
    7. 55
    Prev
    Next
    INDEX
    Explanations

    negated words or words with negative connotations

    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
     apiece
    -0.60
    iál
    -0.58
     подряд
    -0.57
     respectivement
    -0.57
    今度は
    -0.57
    along
    -0.56
     Mather
    -0.56
    ArgumentParser
    -0.56
     postup
    -0.55
     @}
    -0.54
    POSITIVE LOGITS
     not
    1.80
     Not
    1.65
     NOT
    1.57
    not
    1.47
    Not
    1.43
     no
    1.33
    NOT
    1.30
     nicht
    1.27
     tidak
    1.25
     without
    1.20
    Activations Density 4.073%

    No Known Activations