© 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. 14046
    Prev
    Next
    INDEX
    Explanations

    references to content retrieval functions or methods

    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
     
    -0.65
    .
    -0.54
     is
    -0.47
    ,
    -0.47
     on
    -0.46
    ’
    -0.46
    2
    -0.45
    <b>
    -0.45
    <i>
    -0.45
    4
    -0.44
    POSITIVE LOGITS
     newList
    2.14
     appId
    1.79
     eventName
    1.78
     companyId
    1.76
     groupName
    1.72
     bookId
    1.69
     fileSize
    1.68
     eventId
    1.63
     newVal
    1.63
     oldValue
    1.60
    Activations Density 0.010%

    No Known Activations