© 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. 3-RES-MATRYOSHKA-DC
    7. 3181
    Prev
    Next
    INDEX
    Explanations

    scientific journal titles with "PhysRev" in them.

    oai_token-act-pair · gemini-2.0-flash
    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
     FOOT
    -0.46
     foot
    -0.44
    mpa
    -0.41
    ерт
    -0.41
     думать
    -0.41
    unya
    -0.40
     permiti
    -0.40
    foot
    -0.40
    층
    -0.40
     Cot
    -0.40
    POSITIVE LOGITS
    PhysRev
    6.16
    PhysRevLett
    4.19
    PhysRevD
    2.88
    bootstrapcdn
    1.30
     disambiguazione
    1.27
    Diweddarwch
    1.10
     EconPapers
    1.10
     autorytatywna
    1.08
    migrationBuilder
    1.07
    WebElementEntity
    1.07
    Activations Density 0.004%

    No Known Activations