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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3246
    Prev
    Next
    INDEX
    Explanations

    terms related to genetic analysis and testing methodologies

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.86
     traditionnels
    -0.77
     pinulongan
    -0.75
    Nazionale
    -0.73
     متعلقه
    -0.70
    AsUp
    -0.69
     tetanus
    -0.69
    Legături
    -0.68
    Espèce
    -0.67
     للاسماء
    -0.67
    POSITIVE LOGITS
    исленность
    0.56
     moderna
    0.54
     الحدي
    0.50
     modern
    0.47
     оригіналу
    0.47
     Twitter
    0.45
     nouvelles
    0.45
     Heron
    0.44
     inaugural
    0.44
     современ
    0.44
    Activations Density 1.354%

    No Known Activations