© 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. 20853
    Prev
    Next
    INDEX
    Explanations

    terms describing surface texture or quality

    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
     itſelf
    -0.85
     myſelf
    -0.83
     deport
    -0.80
     Enzo
    -0.78
     NSCoder
    -0.77
    ExtendWith
    -0.77
    WebServlet
    -0.76
     glaciers
    -0.76
    Filmographie
    -0.75
     purpoſe
    -0.75
    POSITIVE LOGITS
     Rough
    1.27
    Rough
    1.27
    rough
    1.21
     rough
    1.16
    ghest
    1.07
    ROUGH
    1.02
     Roughly
    1.02
     roughly
    0.94
    roughly
    0.94
     roughness
    0.85
    Activations Density 0.007%

    No Known Activations