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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19241
    Prev
    Next
    INDEX
    Explanations

    instances of the word "one" in various contexts, particularly emphasizing its numerical and singular aspects

    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
    ']))
    -0.68
    '));
    -0.65
    )]);
    -0.65
    ']);
    -0.64
     tami
    -0.63
    )");
    -0.62
    aarrggbb
    -0.61
    )».
    -0.61
     Brunswick
    -0.60
    CrossRef
    -0.59
    POSITIVE LOGITS
     /\.
    0.93
     fleste
    0.89
     flesta
    0.87
    ьаж
    0.84
    endphp
    0.79
    AspNet
    0.76
     Repe
    0.75
    ThroughAttribute
    0.75
     Ome
    0.75
    antMatchers
    0.75
    Activations Density 0.044%

    No Known Activations