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. 31776
    Prev
    Next
    INDEX
    Explanations

    references to indices or notation related to mathematical or statistical frameworks

    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
     purpoſe
    -0.80
     Duane
    -0.79
    Chham
    -0.78
     fhould
    -0.75
     Chichester
    -0.75
     Faust
    -0.73
     reaſon
    -0.73
     Darmstadt
    -0.73
    listo
    -0.72
     pleaſure
    -0.72
    POSITIVE LOGITS
    ij
    1.41
     ij
    0.95
     Zij
    0.95
     Mij
    0.88
    ecap
    0.80
    IJ
    0.73
    ()][
    0.73
     Kij
    0.71
     Lij
    0.68
     IJ
    0.67
    Activations Density 0.023%

    No Known Activations