© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14041
    Prev
    Next
    INDEX
    Explanations

    text that involves code structure and specific keywords related to code components

    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
     Gallimard
    -0.68
     ejus
    -0.67
    ThroughAttribute
    -0.66
    WithMany
    -0.65
     antichi
    -0.62
     auroit
    -0.62
     termica
    -0.60
     biologique
    -0.60
     provinciale
    -0.60
     elettron
    -0.60
    POSITIVE LOGITS
    Datuak
    0.98
      (
    0.65
     дописавши
    0.64
     cherchés
    0.60
     spot
    0.59
    MigrationBuilder
    0.58
    .)}
    0.57
    <eos>
    0.56
    pecially
    0.56
     transfieras
    0.56
    Activations Density 0.820%

    No Known Activations