© 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. 0-RES-MATRYOSHKA-DC
    7. 11529
    Prev
    Next
    INDEX
    Explanations

    diagrams or descriptions related to digital circuitry

    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
     Administration
    -0.49
    ']:
    -0.47
     kark
    -0.46
    izien
    -0.46
     abundant
    -0.45
     folgt
    -0.44
    AlterField
    -0.43
    ';
    -0.43
    ないので
    -0.43
    ThroughAttribute
    -0.43
    POSITIVE LOGITS
    CLK
    3.41
     CLK
    1.44
    Clk
    0.80
     незавершена
    0.72
    TProtocol
    0.68
     AssemblyCulture
    0.66
     doubtnut
    0.66
    stateProvider
    0.64
     OMITBAD
    0.63
     foramen
    0.60
    Activations Density 0.001%

    No Known Activations