© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15825
    Prev
    Next
    INDEX
    Explanations

    references to tactile contact or touching

    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
     touched
    -0.95
     touches
    -0.80
    ClientSize
    -0.68
    WithIOException
    -0.63
     nahilalakip
    -0.60
    StateException
    -0.58
    UnusedPrivate
    -0.57
    jména
    -0.56
     ModelExpression
    -0.56
    MethodManager
    -0.56
    POSITIVE LOGITS
    Touch
    1.76
     Touch
    1.48
    TOUCH
    1.11
    touch
    1.02
     touchdowns
    0.61
     TOUCH
    0.61
     touchdown
    0.60
    rungsseite
    0.53
     autorytatywna
    0.52
    prüche
    0.52
    Activations Density 0.002%

    No Known Activations