© 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. 4-CLT-HP
    7. 2326
    Prev
    Next
    INDEX
    Explanations

    Legal and technical documents

    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
     Moroccan
    -0.46
     őket
    -0.45
    fällig
    -0.44
    lo
    -0.44
    alo
    -0.42
     Morocco
    -0.42
    ilo
    -0.41
    isy
    -0.40
    mator
    -0.40
     Marra
    -0.40
    POSITIVE LOGITS
    StringProperty
    0.65
    amaño
    0.65
    rawDesc
    0.63
    latch
    0.59
     incomplète
    0.59
    modelBuilder
    0.59
    Spoljašnje
    0.57
    ngdoc
    0.57
    ahul
    0.56
    itrile
    0.56
    Activations Density 0.006%

    No Known Activations