© 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. 0-CLT-HP
    4. 38574
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
     متعلقه
    -0.94
     propOrder
    -0.92
    setVerticalGroup
    -0.87
    CloseOperation
    -0.84
     JpaRepository
    -0.81
    -
    -0.79
    حياته
    -0.79
    脚注の使い方
    -0.79
     Administrativna
    -0.79
    etheless
    -0.78
    POSITIVE LOGITS
    <bos>
    0.73
    i
    0.62
    a
    0.61
    e
    0.57
    uk
    0.54
    u
    0.53
    I
    0.53
    in
    0.52
    el
    0.50
    ↵↵
    0.49
    Activations Density 0.132%

    No Known Activations