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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 9-RES-MATRYOSHKA-DC
    4. 16751
    Prev
    Next
    INDEX
    Explanations

    hyphens between words

    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
     invokingState
    -0.87
    Parcelize
    -0.73
     réguli
    -0.66
     saites
    -0.66
     magasiner
    -0.65
    φη
    -0.63
    otient
    -0.62
     Halliday
    -0.60
    ὴν
    -0.59
    reordered
    -0.59
    POSITIVE LOGITS
     חיצוניים
    0.74
     kunci
    0.59
     the
    0.57
     new
    0.57
     tomorrow
    0.57
    ょう
    0.56
     particular
    0.53
    tomorrow
    0.52
    ToAction
    0.48
     anew
    0.48
    Activations Density 0.000%

    No Known Activations