© 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. 2378
    Prev
    Next
    INDEX
    Explanations

    snippets of code

    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
    )";
    -0.87
    /$',
    -0.78
    )"),
    -0.78
    ]`
    -0.77
    帖最后由
    -0.77
    ()")
    -0.75
    ()");
    -0.74
    $")
    -0.73
    ]";
    -0.73
    )");
    -0.73
    POSITIVE LOGITS
     again
    0.96
     Plus
    0.88
     plus
    0.86
    plus
    0.85
    bis
    0.85
    Plus
    0.84
    again
    0.82
     PLUS
    0.80
     Again
    0.77
     II
    0.71
    Activations Density 1.226%

    No Known Activations