© 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. 6353
    Prev
    Next
    INDEX
    Explanations

    uses of form input elements, particularly checkboxes, radio buttons, or range sliders

    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
    type
    -0.54
     type
    -0.52
     sheet
    -0.52
     form
    -0.51
    GraphicsUnit
    -0.51
    ngOnDestroy
    -0.50
    sheet
    -0.49
    WISE
    -0.49
    AxisAlignment
    -0.48
    form
    -0.47
    POSITIVE LOGITS
    SourceChecksum
    0.91
     disponibilités
    0.84
    ніципа
    0.68
    Gemeinden
    0.65
    SharedDtor
    0.64
    évaluateur
    0.62
     fraî
    0.61
     décro
    0.59
     nahilalakip
    0.59
    Diweddarwch
    0.58
    Activations Density 0.214%

    No Known Activations