© 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. 22-RES-MATRYOSHKA-DC
    7. 2230
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially lines within a batch script

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     ujednoznacz
    -0.68
     disambiguazione
    -0.59
     שוליים
    -0.57
    styleType
    -0.56
     الحره
    -0.50
    ouldering
    -0.48
    énario
    -0.48
    مصادر
    -0.46
     useContext
    -0.46
    olc
    -0.45
    POSITIVE LOGITS
    isei
    0.60
     "%
    0.59
    pause
    0.56
    PAUSE
    0.56
     %
    0.56
    ;%
    0.55
     pause
    0.54
    "%
    0.54
     goto
    0.53
    =%
    0.53
    Activations Density 0.047%

    No Known Activations