© 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. 15328
    Prev
    Next
    INDEX
    Explanations

    references to specific researchers and their work

    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
    errHandler
    -0.71
    الحياه
    -0.70
     '\\;'
    -0.70
     appunt
    -0.68
    foreignKey
    -0.68
     Theſe
    -0.68
    smithy
    -0.64
     AttributeSet
    -0.63
    SizeMode
    -0.62
     Conſ
    -0.62
    POSITIVE LOGITS
    fh
    1.40
    gants
    1.15
    lant
    1.09
     Wrote
    1.00
    bian
    0.83
    ctose
    0.75
    lants
    0.73
     fructose
    0.66
    bians
    0.54
     closing
    0.49
    Activations Density 0.002%

    No Known Activations