© 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. 33
    Prev
    Next
    INDEX
    Explanations

    code keywords and functions, often related to C++ or similar syntax, and identifiers, sometimes within the context of asserts or invariants.

    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
    "));
    -1.25
    '));
    -1.23
    ']);
    -1.21
    ")));
    -1.17
    '))
    -1.14
    ()));
    -1.14
    "))
    -1.09
    ")){
    -1.09
     ");
    -1.09
    "];
    -1.09
    POSITIVE LOGITS
     myſelf
    1.46
     pleaſure
    1.44
     purpoſe
    1.39
     Jefus
    1.39
     Monfieur
    1.38
     Reſ
    1.34
     itſelf
    1.34
     Eſ
    1.29
     Anſ
    1.29
     Majefty
    1.27
    Activations Density 7.573%

    No Known Activations