© 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. 2-RES-MATRYOSHKA-DC
    7. 6846
    Prev
    Next
    INDEX
    Explanations

    instances of negation or exclusion

    oai_token-act-pair · gpt-4.1-nano
    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
     cannot
    -0.66
    estu
    -0.65
     никаких
    -0.62
     Dillon
    -0.60
     هیچ
    -0.59
     Khart
    -0.59
    dii
    -0.58
     McIntyre
    -0.57
    cannot
    -0.55
     dorada
    -0.55
    POSITIVE LOGITS
    Not
    1.36
     Not
    1.33
    not
    1.25
    NOT
    1.17
     not
    1.15
     NOT
    1.06
    RectangleBorder
    0.81
     betweenstory
    0.79
    pushFollow
    0.75
    AsUp
    0.73
    Activations Density 0.170%

    No Known Activations