© 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. 6-RES-MATRYOSHKA-DC
    7. 1006
    Prev
    Next
    INDEX
    Explanations

    code documentation comment blocks with asterisks

    oai_token-act-pair · gemini-2.0-flash
    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
     disambiguazione
    -0.73
    ьаж
    -0.71
    Personensuche
    -0.69
    RefNanny
    -0.66
    enterOuterAlt
    -0.66
    EndContext
    -0.65
     GetEnumerator
    -0.63
     knots
    -0.62
     незавершена
    -0.62
     Roskov
    -0.61
    POSITIVE LOGITS
     raiſ
    0.57
    iestety
    0.57
     """
    0.56
     "
    0.56
     Jérusalem
    0.54
     tana
    0.52
     ulong
    0.51
    OrNil
    0.51
    ὖ
    0.50
    $.
    0.49
    Activations Density 0.101%

    No Known Activations