© 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. 2800
    Prev
    Next
    INDEX
    Explanations

    references to official sources or authorities

    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
     referenties
    -0.65
     InputDecoration
    -0.62
    providedIn
    -0.60
     שוליים
    -0.59
    Geplaatst
    -0.58
     Pilate
    -0.58
    batore
    -0.57
    Parm
    -0.57
    Profession
    -0.56
    Profes
    -0.56
    POSITIVE LOGITS
     official
    3.44
    official
    3.16
    Official
    3.14
     Official
    3.13
     OFFICIAL
    3.02
    OFFICIAL
    2.78
     oficial
    2.56
     officially
    2.39
     officiel
    2.36
     ufficiale
    2.17
    Activations Density 0.013%

    No Known Activations