© 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. 14132
    Prev
    Next
    INDEX
    Explanations

    references to the word "comb" or its variations

    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
    endphp
    -0.67
     iprot
    -0.56
    amom
    -0.55
    totalPages
    -0.54
     JNI
    -0.54
     Lem
    -0.53
     nao
    -0.53
    ,:),
    -0.51
    IndentedString
    -0.51
    bayan
    -0.49
    POSITIVE LOGITS
     comb
    3.53
     combs
    2.66
     Comb
    2.11
     combed
    1.89
     combing
    1.79
    Comb
    1.71
     COMB
    1.18
     Combs
    0.92
    櫛
    0.82
    comb
    0.77
    Activations Density 0.001%

    No Known Activations