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. 30962
    Prev
    Next
    INDEX
    Explanations

    the word "to" followed closely by a verb

    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
     continuing
    -0.60
    ve
    -0.54
     missed
    -0.50
     following
    -0.48
     Stoff
    -0.48
    chute
    -0.47
    ive
    -0.46
     last
    -0.46
     proceeding
    -0.46
     Continuing
    -0.46
    POSITIVE LOGITS
    expandindo
    0.92
    (!__
    0.79
     resourceCulture
    0.75
    parsedMessage
    0.75
    WithIOException
    0.69
    ConverterFactory
    0.68
    insics
    0.68
     htmlFor
    0.68
     truce
    0.68
     onResponse
    0.68
    Activations Density 0.010%

    No Known Activations