© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14006
    Prev
    Next
    INDEX
    Explanations

    references to a specific chemical compound, likely "opa," "synchrotron," or "hibitor."

    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
     bezeichneter
    -0.75
     surla
    -0.71
    ]--;
    -0.69
     Italijani
    -0.68
     дописавши
    -0.67
    %)$
    -0.67
     CreateTagHelper
    -0.65
    มาะ
    -0.65
     autorytatywna
    -0.63
     HasFactory
    -0.63
    POSITIVE LOGITS
    AppMethodBeat
    0.82
    gwt
    0.66
     **/
    0.59
    opa
    0.59
     Kosovo
    0.58
     Paz
    0.57
    ::~
    0.55
    labelledby
    0.55
     altern
    0.53
    **/
    0.52
    Activations Density 0.143%

    No Known Activations