Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 31336
    Prev
    Next
    INDEX
    Explanations

    Latex math delimiters and variables.

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.77
    ngdoc
    -0.76
    VersionUID
    -0.75
     buckwheat
    -0.71
    chyma
    -0.69
     Paulina
    -0.69
     anhydrous
    -0.69
     Monfieur
    -0.69
    enment
    -0.69
     Reverso
    -0.69
    POSITIVE LOGITS
    '))
    
    0.67
    >';
    
    0.65
    ")));
    
    0.62
     an
    0.60
    "))
    
    0.60
     he
    0.56
     the
    0.56
    ':
    
    0.56
    '));
    
    0.56
    ++;
    
    0.55
    Activations Density 0.025%

    No Known Activations