© 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. 5-CLT-HP
    7. 93977
    Prev
    Next
    INDEX
    Explanations

    river

    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
    AsUp
    -0.56
    ubon
    -0.48
     mensuales
    -0.46
     econó
    -0.45
     biblioteca
    -0.43
    WebVitals
    -0.43
     Testamento
    -0.43
    czki
    -0.43
     grito
    -0.42
     bomba
    -0.42
    POSITIVE LOGITS
    ine
    0.68
    Bronnen
    0.65
    INE
    0.63
     corridors
    0.60
     channel
    0.60
    ANNELS
    0.58
    stdc
    0.57
     corridor
    0.57
    لیس
    0.57
     channels
    0.56
    Activations Density 0.000%

    No Known Activations