Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14598
    Prev
    Next
    INDEX
    Explanations

    occurrences of mathematical expressions involving numeric values, particularly those with dollar signs, exponents, and equal signs

    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
     itſelf
    -1.40
     myſelf
    -1.30
     Efq
    -1.21
     Jefus
    -1.20
     ―――――
    -1.20
     Houſe
    -1.20
    tvguidetime
    -1.19
     Monfieur
    -1.18
     Majefty
    -1.16
     $_"
    -1.16
    POSITIVE LOGITS
     
    1.01
    $
    0.99
     $
    0.98
    .
    0.86
    <eos>
    0.82
     $\
    0.78
    '
    0.78
    $\
    0.73
    __))
    0.71
    ↵↵
    0.69
    Activations Density 0.524%

    No Known Activations