© 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. 2-RES-MATRYOSHKA-DC
    7. 4970
    Prev
    Next
    INDEX
    Explanations

    code for handling errors and system return 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
     Tula
    -0.66
     NSCoder
    -0.66
     InputDecoration
    -0.63
    ngdoc
    -0.59
    ,:);
    -0.56
     Lank
    -0.55
    alogie
    -0.55
    KURZBESCHREIBUNG
    -0.54
     AssemblyVersion
    -0.54
    olstein
    -0.53
    POSITIVE LOGITS
    ret
    2.98
     ret
    2.63
    Ret
    2.48
     Ret
    2.39
    RET
    1.93
     RET
    1.80
    rets
    1.48
    RETT
    1.43
    retten
    1.35
    rett
    1.34
    Activations Density 0.035%

    No Known Activations