© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5128
    Prev
    Next
    INDEX
    Explanations

    references to the mouth or mouthpiece, often in the context of devices or interactions involving the mouth

    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
     jegy
    -0.66
    Autoritní
    -0.65
     Picchu
    -0.55
    putExtra
    -0.54
    колай
    -0.54
     gaps
    -0.52
    nitzel
    -0.51
    InSection
    -0.51
    WithTag
    -0.51
     tea
    -0.50
    POSITIVE LOGITS
     mouth
    4.03
     Mouth
    3.70
    mouth
    3.48
     mouths
    3.38
    Mouth
    3.36
    mouthed
    2.55
    MOUTH
    2.52
     bouche
    2.16
     mout
    2.14
     bocca
    2.02
    Activations Density 0.020%

    No Known Activations