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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 30918
    Prev
    Next
    INDEX
    Explanations

    numbers, particularly those used as indices or representing numerical data

    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
     Exactos
    -0.90
    CrossRef
    -0.86
     useContext
    -0.71
    InstanceState
    -0.71
    原始内容存档于
    -0.70
     оригіналу
    -0.69
    Gambas
    -0.67
    GroupLayout
    -0.66
     Manas
    -0.64
     שוליים
    -0.63
    POSITIVE LOGITS
    "];
    
    0.56
    kegaard
    0.56
    jsonwebtoken
    0.56
    "]));
    0.54
    "]);
    
    0.54
    "])
    
    0.54
    ]));
    
    0.53
    المناصب
    0.53
    '];
    
    0.51
    ]");
    0.51
    Activations Density 0.040%

    No Known Activations