© 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. 3356
    Prev
    Next
    INDEX
    Explanations

    references to scientific concepts and techniques in biochemical research

    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
     enfans
    -0.77
     synthèse
    -0.73
     AssemblyCompany
    -0.73
    Hentet
    -0.72
     autorité
    -0.71
     autoridade
    -0.71
     idéia
    -0.68
     redeem
    -0.67
     endforeach
    -0.67
     équilibre
    -0.67
    POSITIVE LOGITS
     need
    0.69
     lack
    0.68
     use
    0.60
     increasing
    0.59
     being
    0.57
     finding
    0.57
     increased
    0.56
     limited
    0.56
     having
    0.53
     also
    0.52
    Activations Density 0.448%

    No Known Activations