© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1115
    Prev
    Next
    INDEX
    Explanations

    shell and makefile snippets

    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
    )";
    -0.98
    )");
    -0.81
    })));
    -0.80
    };*/
    -0.79
    ...");
    -0.77
    ."));
    -0.76
    "]);
    -0.75
    %");
    -0.75
    }));
    -0.73
    ")));
    -0.73
    POSITIVE LOGITS
     $(
    0.70
     $
    0.58
     $-
    0.56
     -
    0.56
     "${
    0.54
     "$
    0.53
     ${
    0.50
     "
    0.49
     ilgi
    0.48
     --
    0.48
    Activations Density 0.841%

    No Known Activations