© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 32220
    Prev
    Next
    INDEX
    Explanations

    references to genetic sequences or identifiers

    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
     kasarigan
    -0.84
     ſind
    -0.82
    )"),
    -0.79
    clyde
    -0.78
     Reſ
    -0.77
    "):
    -0.74
    featureID
    -0.74
    StructEnd
    -0.73
     myſelf
    -0.72
    CopyWith
    -0.72
    POSITIVE LOGITS
    abestanden
    0.46
     saja
    0.44
    Einzelnachweise
    0.42
     for
    0.40
    lamak
    0.39
    Abitanti
    0.38
     rather
    0.37
    '
    0.37
    aterdag
    0.36
     battre
    0.36
    Activations Density 0.008%

    No Known Activations