© 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. 17499
    Prev
    Next
    INDEX
    Explanations

    references to tape and its related components or uses

    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
     pros
    -0.76
     Lowry
    -0.74
    noah
    -0.71
    </h1>
    -0.68
    院
    -0.66
     Pros
    -0.65
    _^
    -0.65
     Matthews
    -0.65
     Miller
    -0.64
     Biggs
    -0.63
    POSITIVE LOGITS
     tapes
    1.64
     Tape
    1.63
     tape
    1.63
    Tape
    1.59
     Tapes
    1.51
     TAPE
    1.50
    tape
    1.45
     taping
    1.38
    tapes
    1.34
     TAP
    1.33
    Activations Density 0.035%

    No Known Activations