© 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. 11147
    Prev
    Next
    INDEX
    Explanations

    workaround instructions or suggestions

    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
    ValueStyle
    -0.56
     án
    -0.49
    χύ
    -0.47
    kee
    -0.47
     colspan
    -0.46
     Ney
    -0.46
    städ
    -0.46
    igen
    -0.44
    แล้ว
    -0.43
    amu
    -0.43
    POSITIVE LOGITS
     workaround
    1.45
    fallback
    0.99
     therefor
    0.91
     fallback
    0.79
    GEBURTSDATUM
    0.78
    oasis
    0.75
     JpaRepository
    0.75
    contr
    0.74
     CAG
    0.74
     disambiguazione
    0.73
    Activations Density 0.023%

    No Known Activations