© 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. 14076
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Cos" or variations thereof

    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
    XtraGrid
    -0.51
     Robb
    -0.49
     '-';
    -0.48
    니다
    -0.47
     AttributeSet
    -0.47
    المشاركات
    -0.47
    ())))
    -0.46
    quiti
    -0.46
    AttributeSet
    -0.45
    :"-
    -0.44
    POSITIVE LOGITS
     Cos
    2.95
    Cos
    2.52
     cos
    1.98
     COS
    1.71
    COS
    1.23
     Cosmo
    1.06
     cosmo
    0.98
     Cosby
    0.94
     cosme
    0.94
    Cosmo
    0.90
    Activations Density 0.001%

    No Known Activations