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. 12-RES-MATRYOSHKA-DC
    4. 15315
    Prev
    Next
    INDEX
    Explanations

    discussions of significance and implications in scientific contexts

    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
    httphttps
    -0.75
     sukienka
    -0.64
     humaines
    -0.64
    expandindo
    -0.62
    IntoConstraints
    -0.61
    Xna
    -0.60
    cektir
    -0.58
    yordu
    -0.57
     offerta
    -0.56
    spania
    -0.56
    POSITIVE LOGITS
     >=",
    0.55
    '},
    
    0.53
    .';
    0.52
    ]');
    0.51
    '});
    0.50
    %");
    0.49
    äsident
    0.49
     Haft
    0.48
     fil
    0.47
    }');
    0.47
    Activations Density 0.095%

    No Known Activations