© 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. 1434
    Prev
    Next
    INDEX
    Explanations

    names of individuals and entities related to different fields and 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
    neſs
    -0.63
     }}$}
    -0.62
     devenus
    -0.62
     ſy
    -0.59
    Hentet
    -0.59
    noinspection
    -0.59
     Efq
    -0.58
     ſtate
    -0.57
     reaſon
    -0.56
     Taktlose
    -0.56
    POSITIVE LOGITS
    SequentialGroup
    0.71
     kasarigan
    0.60
    <eos>
    0.59
    ParallelGroup
    0.55
     is
    0.54
     Numerade
    0.52
    NameInMap
    0.52
    aarrggbb
    0.51
     تانيه
    0.49
    itology
    0.49
    Activations Density 3.665%

    No Known Activations