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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 31100
    Prev
    Next
    INDEX
    Explanations

    code blocks with parentheses

    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
    urcht
    -0.65
     nici
    -0.64
    djangoproject
    -0.63
     déput
    -0.62
    ConstraintMaker
    -0.60
    Tikang
    -0.60
     nicio
    -0.58
    AddTagHelper
    -0.58
     partecipazione
    -0.57
    Попис
    -0.56
    POSITIVE LOGITS
     GenerationType
    0.83
    CROSSTALK
    0.62
     AspNetCore
    0.61
     OE
    0.55
    Rango
    0.54
    lendir
    0.54
     Crosse
    0.53
     carter
    0.52
     Px
    0.52
    iteiten
    0.51
    Activations Density 0.003%

    No Known Activations