© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11570
    Prev
    Next
    INDEX
    Explanations

    factual statements and key issues related to decision-making and clarification

    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
     totalité
    -0.61
     stør
    -0.57
     exact
    -0.56
    Климат
    -0.55
     entire
    -0.54
    EXACT
    -0.54
     segala
    -0.53
    annica
    -0.53
    Entire
    -0.51
     piedi
    -0.50
    POSITIVE LOGITS
    SOME
    0.85
     some
    0.84
    some
    0.81
    PerformLayout
    0.75
    Some
    0.74
     Some
    0.73
     nakalista
    0.72
     المعيارى
    0.72
     SOME
    0.71
     فريبيس
    0.71
    Activations Density 0.264%

    No Known Activations