© 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. 5-CLT-HP
    7. 884
    Prev
    Next
    INDEX
    Explanations

    Code and punctuation

    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
     initComponents
    -0.56
    Carriera
    -0.55
     상세
    -0.53
    omitempty
    -0.52
    élica
    -0.52
     történ
    -0.51
    EditorBrowsable
    -0.48
    Lugar
    -0.47
     produced
    -0.47
    Ծանոթ
    -0.47
    POSITIVE LOGITS
    rungsseite
    0.95
    IntoConstraints
    0.56
     Buying
    0.53
    Rüyada
    0.53
    Hozzáférés
    0.52
     typelib
    0.50
    OMON
    0.50
    >|</
    0.50
    ьа
    0.49
    Geplaatst
    0.47
    Activations Density 0.005%

    No Known Activations