© 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. 3396
    Prev
    Next
    INDEX
    Explanations

    references to specific words or phrases related to "Touch" and "Way," indicating it detects mentions of tactile interactions or methods

    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
    ########.
    -0.59
    новништво
    -0.55
    +#+#
    -0.52
    VersionUID
    -0.51
    
    -0.51
    amarin
    -0.51
    tivität
    -0.50
    complexContent
    -0.50
     stiefel
    -0.49
    tadiene
    -0.49
    POSITIVE LOGITS
    Vanjske
    0.65
    ChildScrollView
    0.63
     مشين
    0.60
     חיצוניים
    0.59
     tarts
    0.59
    ViewFeatures
    0.56
    iecie
    0.55
    XtraReports
    0.55
    ntgen
    0.55
    Collegamenti
    0.54
    Activations Density 0.304%

    No Known Activations