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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 30915
    Prev
    Next
    INDEX
    Explanations

    the word "if", sometimes along with the pronoun "I"

    oai_token-act-pair · gemini-2.0-flash
    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
     If
    -0.85
    If
    -0.79
    if
    -0.74
     varsa
    -0.63
    要是
    -0.62
     Если
    -0.62
     if
    -0.61
    IF
    -0.61
     Якщо
    -0.60
    があれば
    -0.60
    POSITIVE LOGITS
     виправивши
    0.90
    tvguidetime
    0.89
    IntoConstraints
    0.85
    [++
    0.85
    AndEndTag
    0.80
     AssemblyProduct
    0.78
    AccessorTable
    0.77
     ModelExpression
    0.77
     &___
    0.75
    endpush
    0.75
    Activations Density 0.038%

    No Known Activations