© 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. 5-CLT-HP
    4. 2637
    Prev
    Next
    INDEX
    Explanations

    component

    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
    qrstuvwxyz
    -0.53
     Fact
    -0.49
     branche
    -0.46
    🏻
    -0.46
     '/':
    -0.45
    Lähteet
    -0.44
    mities
    -0.43
    nese
    -0.43
    auté
    -0.42
     '*':
    -0.42
    POSITIVE LOGITS
    HasForeignKey
    0.84
     autorytatywna
    0.70
    UnusedPrivate
    0.66
    EDEFAULT
    0.61
    Revenir
    0.60
    BASEPATH
    0.59
    getOut
    0.59
    TextWatcher
    0.58
    sizeCache
    0.58
    ніципа
    0.58
    Activations Density 0.005%

    No Known Activations