© 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. 14303
    Prev
    Next
    INDEX
    Explanations

    highly technical language and structured code comments

    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
    }>;
    -0.97
    ]-->
    -0.93
    __*/
    -0.91
     nonatomic
    -0.90
    Ծանոթ
    -0.90
    ]")]
    -0.88
     MainAxisSize
    -0.85
     getItemId
    -0.84
    extAlignment
    -0.84
     StatefulWidget
    -0.84
    POSITIVE LOGITS
     ansatte
    0.54
    Contrato
    0.49
    <sup>
    0.48
    </strong>
    0.47
    <strong>
    0.46
     Keyes
    0.46
     he
    0.45
    ROOT
    0.45
     applied
    0.45
    /
    0.45
    Activations Density 0.001%

    No Known Activations