© 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. 43880
    Prev
    Next
    INDEX
    Explanations

    TD

    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
    tish
    -0.60
    arik
    -0.60
     وتسجيلات
    -0.59
     dem
    -0.57
     تضيفلها
    -0.56
    hirt
    -0.53
    ent
    -0.53
    teer
    -0.53
    etheless
    -0.52
    BindingResult
    -0.51
    POSITIVE LOGITS
    
    0.83
    glEnd
    0.71
     Jurí
    0.61
    مئ
    0.58
    hiasan
    0.58
     gevo
    0.57
     panel
    0.56
    :+:
    0.55
     Grub
    0.55
    Jude
    0.55
    Activations Density 0.681%

    No Known Activations