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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13910
    Prev
    Next
    INDEX
    Explanations

    references to scholarly or technical data, methods, or specific terminology

    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
     disambiguazione
    -0.87
     resourceCulture
    -0.75
     TextAppearance
    -0.68
    iastical
    -0.64
    ApiModelProperty
    -0.63
    ,$_
    -0.63
    日閲覧
    -0.61
     fortn
    -0.61
    noinspection
    -0.60
    AndEndTag
    -0.60
    POSITIVE LOGITS
    heed
    0.67
    gwt
    0.67
    FORMAT
    0.66
    iseries
    0.62
     convertView
    0.60
    pwd
    0.59
    #+#
    0.57
    clair
    0.56
    bald
    0.55
    formik
    0.55
    Activations Density 0.091%

    No Known Activations