© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 56
    Prev
    Next
    INDEX
    Explanations

    words and phrases that act as headings

    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
    Personendaten
    -1.34
     мәкал
    -1.27
    MigrationBuilder
    -1.27
    Datuak
    -1.22
    Personensuche
    -1.17
    EndGlobalSection
    -1.16
    клопе
    -1.14
    ########.
    -1.11
     AssemblyTitle
    -1.07
     Савезне
    -1.06
    POSITIVE LOGITS
    ↵↵
    0.67
    ,
    0.66
    .
    0.66
     
    0.64
     the
    0.63
     e
    0.62
     in
    0.60
     I
    0.60
     a
    0.59
     to
    0.59
    Activations Density 16.096%

    No Known Activations