© 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. 2-RES-MATRYOSHKA-DC
    7. 2542
    Prev
    Next
    INDEX
    Explanations

    the concept of unknown or unspecified information

    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
    %")
    -0.64
     know
    -0.62
    %");
    -0.60
    annica
    -0.56
     un
    -0.55
    siel
    -0.53
    utiva
    -0.53
    ++]=
    -0.51
     infatti
    -0.50
    %]
    -0.50
    POSITIVE LOGITS
     unknown
    3.25
    unknown
    2.89
     Unknown
    2.83
    Unknown
    2.52
     UNKNOWN
    2.52
     unknowns
    2.34
     inconn
    2.16
    未知
    2.09
     desconhe
    2.09
     неизвест
    2.03
    Activations Density 0.055%

    No Known Activations