© 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. 4908
    Prev
    Next
    INDEX
    Explanations

    references to a significant or contrasting change or variation

    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
     InputDecoration
    -0.55
    Other
    -0.54
    extField
    -0.53
    Others
    -0.53
     rendu
    -0.52
     demás
    -0.52
    المناصب
    -0.52
    Obrázky
    -0.51
     tavolo
    -0.50
     née
    -0.50
    POSITIVE LOGITS
    ziel
    0.65
     same
    0.64
     #"
    0.63
    )|\
    0.63
     neuem
    0.63
    chong
    0.62
    醐
    0.61
     Permalink
    0.59
    SourceChecksum
    0.59
    gatsby
    0.59
    Activations Density 0.192%

    No Known Activations