© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38342
    Prev
    Next
    INDEX
    Explanations

    filter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     filter
    -1.40
     filters
    -1.30
     Filter
    -1.16
     filtro
    -1.11
     Filters
    -1.09
     filtros
    -1.09
    filter
    -1.08
     Filtering
    -1.06
     filtering
    -1.05
     FILTER
    -1.05
    POSITIVE LOGITS
    StructEnd
    0.55
    neau
    0.52
     rech
    0.48
     تكبرها
    0.47
     poveznice
    0.47
    REY
    0.46
    AddTagHelper
    0.44
    leyeb
    0.44
     Gea
    0.44
    er
    0.43
    Activations Density 0.076%

    No Known Activations