© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1026
    Prev
    Next
    INDEX
    Explanations

    the word "primary", sometimes along with related terms like "structures", "care", or "secondary"

    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
    ByKey
    -0.56
    ff
    -0.55
    out
    -0.55
    hoz
    -0.54
     Worth
    -0.52
    Gio
    -0.52
     Guzmán
    -0.52
    pos
    -0.52
     important
    -0.50
    пах
    -0.50
    POSITIVE LOGITS
     primary
    3.36
     Primary
    3.13
    primary
    3.06
    Primary
    3.06
     PRIMARY
    3.02
    PRIMARY
    2.89
     primaire
    2.58
     primaries
    2.41
     primaria
    2.36
     primario
    2.22
    Activations Density 0.066%

    No Known Activations