© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74796
    Prev
    Next
    INDEX
    Explanations

    place names

    np_max-act-logits · 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
    Rhestr
    -0.62
    adaptiveStyles
    -0.59
    évaluateur
    -0.56
     betweenstory
    -0.56
     Dage
    -0.54
    lapi
    -0.52
    msgTypes
    -0.51
    Naissance
    -0.50
    ceptre
    -0.50
     Gent
    -0.50
    POSITIVE LOGITS
    بوابة
    0.53
     متعلقه
    0.46
    soka
    0.46
    alone
    0.43
    Gambas
    0.42
    Dakota
    0.42
    Superview
    0.41
    حوال
    0.41
    Hok
    0.41
    bayan
    0.40
    Activations Density 0.001%

    No Known Activations