© 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. 8821
    Prev
    Next
    INDEX
    Explanations

    certain mathematical structures, particularly related to bounds and functions in statistical models

    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
     Commen
    -0.50
     heck
    -0.45
    сион
    -0.45
    pirable
    -0.45
     Lubric
    -0.43
     Fai
    -0.43
     Paths
    -0.43
    réhen
    -0.43
    creativecommons
    -0.42
     correta
    -0.42
    POSITIVE LOGITS
    TagMode
    0.81
     للمعارف
    0.69
    VELAND
    0.67
    sidemargin
    0.67
    **/
    0.67
    ServletException
    0.66
    BufferException
    0.63
    verifyException
    0.62
     tartalomajánló
    0.61
    Personensuche
    0.59
    Activations Density 0.007%

    No Known Activations