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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4827
    Prev
    Next
    INDEX
    Explanations

    references to seeds and seed-related terms

    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
     ***/
    -0.89
    `]
    -0.85
     Frie
    -0.76
     Cougars
    -0.74
    Życiorys
    -0.73
    onomía
    -0.72
    oporosis
    -0.71
     Fortran
    -0.70
    Bibliografie
    -0.69
    uxxxx
    -0.69
    POSITIVE LOGITS
     seeds
    1.99
     Seeds
    1.84
    Seeds
    1.77
     seed
    1.76
    seed
    1.73
     Seed
    1.67
    seeds
    1.66
    Seed
    1.64
    SEED
    1.62
     SEED
    1.59
    Activations Density 0.011%

    No Known Activations