© 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. 6430
    Prev
    Next
    INDEX
    Explanations

    specifications, settings, and parameters in code or structured data

    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
    хьтан
    -0.56
     strøm
    -0.51
     poupée
    -0.49
    maksud
    -0.48
     charité
    -0.48
    Népesség
    -0.47
     sukker
    -0.46
     dår
    -0.46
    
    -0.45
     dieux
    -0.44
    POSITIVE LOGITS
    homonymie
    0.85
    DockStyle
    0.81
    PhysRevD
    0.79
     '\\;'
    0.74
    MigrationBuilder
    0.74
    Abitanti
    0.73
    asymp
    0.71
    idue
    0.70
    httphttps
    0.68
    
    0.67
    Activations Density 0.062%

    No Known Activations