© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11255
    Prev
    Next
    INDEX
    Explanations

    mathematical equivalences or equalities in terms of relationships between expressions

    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
    =?";
    -0.61
    };*/
    -0.59
    ismen
    -0.56
    zeczytaj
    -0.54
    __':
    -0.53
    ificantly
    -0.52
     caufe
    -0.52
    ;*/
    -0.50
    =*/
    -0.50
    )))));
    -0.49
    POSITIVE LOGITS
    principalTable
    0.60
     naudoti
    0.60
     محفوظة
    0.59
    بوابة
    0.58
     kasarigan
    0.57
    Rüyada
    0.56
     cdti
    0.55
    ждую
    0.54
     ouvertes
    0.54
    equiv
    0.53
    Activations Density 0.001%

    No Known Activations