© 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. 2-RES-MATRYOSHKA-DC
    7. 6929
    Prev
    Next
    INDEX
    Explanations

    expressions of familiarity or recognition involving sounds or speech

    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
     Turnover
    -0.44
     Penit
    -0.42
     ''),
    -0.41
    ingi
    -0.40
     critic
    -0.39
     turnover
    -0.39
     smooth
    -0.39
     McDonough
    -0.39
     Denk
    -0.39
     respetu
    -0.38
    POSITIVE LOGITS
     Audiodateien
    0.81
    الإنجليزية
    0.78
    UnitTesting
    0.75
    marshaller
    0.74
    VIAF
    0.72
     @"/
    0.71
    mobileqq
    0.71
     "..\..\..\
    0.70
    hysema
    0.69
    jsdelivr
    0.69
    Activations Density 1.051%

    No Known Activations