© 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. 0-RES-MATRYOSHKA-DC
    7. 14396
    Prev
    Next
    INDEX
    Explanations

    patterns of numerical and alphanumeric sequences, especially those associated with scientific data, measurements, or technical codes

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ecotoxicity
    -0.59
    gridx
    -0.55
    ]++;
    -0.52
    ChildScrollView
    -0.52
    $_['
    -0.51
     ProtoMessage
    -0.50
    GEBURTS
    -0.50
     Tôi
    -0.49
    RoutingModule
    -0.49
    atzen
    -0.49
    POSITIVE LOGITS
    ####
    2.89
     ####
    1.41
    #####
    1.03
    enumi
    0.94
     #####
    0.75
    <h4>
    0.66
     referrerpolicy
    0.66
     Infórmanos
    0.65
     MotionEvent
    0.64
    enumii
    0.59
    Activations Density 0.001%

    No Known Activations