© 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. 5651
    Prev
    Next
    INDEX
    Explanations

    references to specific data size measurements in the context of data processing or storage

    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
     insuffisamment
    -0.60
    dubbo
    -0.47
     pick
    -0.47
    vor
    -0.46
    ----------------
    -0.45
    ��������
    -0.45
                                   
    -0.45
    ****************
    -0.44
    :-
    -0.44
     treo
    -0.44
    POSITIVE LOGITS
    dL
    1.45
     mL
    1.27
     dB
    1.27
    mL
    1.26
     mA
    1.24
     mV
    1.16
     eV
    1.09
     kB
    1.09
    aA
    1.09
    qJ
    1.09
    Activations Density 0.034%

    No Known Activations