© 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. 5788
    Prev
    Next
    INDEX
    Explanations

    negation or denial indicators

    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
    NotBe
    -0.79
    Ikke
    -0.68
    Autoritní
    -0.68
    Bukan
    -0.66
     enggak
    -0.64
     Bukan
    -0.63
    LoadScene
    -0.62
     nggak
    -0.61
    تقاوى
    -0.61
     Roskov
    -0.60
    POSITIVE LOGITS
    httphttps
    0.82
    maktadır
    0.70
    󠁿
    0.68
    providedIn
    0.66
     attend
    0.65
     Gericht
    0.64
    gensen
    0.63
     fieldNum
    0.62
    newArrayList
    0.62
    AndEndTag
    0.60
    Activations Density 0.096%

    No Known Activations