© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 414
    Prev
    Next
    INDEX
    Explanations

    negative terms or expressions indicating absence or lack

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    toJSONString
    -0.49
    ěj
    -0.47
    complexType
    -0.47
    ScopeManager
    -0.46
    PDT
    -0.46
    LPT
    -0.46
     IST
    -0.46
     einverstanden
    -0.45
    SWR
    -0.45
    ˑ
    -0.44
    POSITIVE LOGITS
     no
    1.19
     No
    1.07
    No
    1.06
     none
    0.94
     without
    0.88
     NO
    0.86
    aucun
    0.85
    Keine
    0.84
    no
    0.82
     None
    0.81
    Activations Density 0.881%

    No Known Activations