© 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. 14078
    Prev
    Next
    INDEX
    Explanations

    references to the most intense or prominent descriptions of visual or sensory features

    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
    AccessorTable
    -0.63
     last
    -0.60
     Has
    -0.57
    topped
    -0.56
     od
    -0.55
    ɒ
    -0.54
     leading
    -0.53
     minimum
    -0.53
     top
    -0.51
    netti
    -0.51
    POSITIVE LOGITS
     strongest
    1.40
     fairest
    1.34
     healthiest
    1.31
     cleanest
    1.30
     brightest
    1.30
     wisest
    1.20
     funniest
    1.19
     clearest
    1.18
     sweetest
    1.17
     purest
    1.17
    Activations Density 0.042%

    No Known Activations