© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 10470
    Prev
    Next
    INDEX
    Explanations

    locations of complete absence or emptiness

    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
    Negative Logits
     saites
    -0.55
     including
    -0.46
    ureux
    -0.45
     etc
    -0.45
    reise
    -0.44
    istoitu
    -0.44
    delà
    -0.43
    等
    -0.43
    illet
    -0.42
     Including
    -0.42
    POSITIVE LOGITS
     nowhere
    3.59
     Nowhere
    2.30
    Nowhere
    2.06
    RenderAtEndOf
    0.74
     betweenstory
    0.72
     يتيمه
    0.71
     nulle
    0.69
    QMetaType
    0.66
    Atsauces
    0.63
     argint
    0.63
    Activations Density 0.000%

    No Known Activations