© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13257
    Prev
    Next
    INDEX
    Explanations

    references to evaluation or measurement tools, such as checklists or lists of assessments

    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
    ="@+
    -0.73
    IActionResult
    -0.71
    JpaRepository
    -0.71
    Schriften
    -0.66
     defaultstate
    -0.65
     getItemId
    -0.64
    __((
    -0.63
     समीक्षाएं
    -0.63
     الرياضيه
    -0.63
    ooplankton
    -0.63
    POSITIVE LOGITS
     lists
    2.09
     Lists
    1.66
    Lists
    1.44
    lists
    1.14
     listas
    0.96
     listes
    0.92
    LISTS
    0.61
     checklists
    0.54
     houses
    0.54
     obě
    0.50
    Activations Density 0.003%

    No Known Activations