© 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. 20177
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical or coding data patterns

    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
     XCTest
    -0.65
     seuls
    -0.57
    Entire
    -0.57
     meurt
    -0.56
     étrangers
    -0.54
     közül
    -0.54
     begitu
    -0.53
     purport
    -0.53
     stdClass
    -0.52
     identifiés
    -0.51
    POSITIVE LOGITS
    initializeApp
    0.91
    bootstrapcdn
    0.73
    enumii
    0.72
    TargetException
    0.71
    findpost
    0.66
    qrstuvwxyz
    0.65
    GraphicsUnit
    0.65
    uxxxx
    0.62
     فريبيس
    0.61
     Prost
    0.60
    Activations Density 0.075%

    No Known Activations