© 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. 94914
    Prev
    Next
    INDEX
    Explanations

    amounts or levels

    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
    UnusedPrivate
    -0.63
    Xna
    -0.57
    |}{\
    -0.54
     propOrder
    -0.53
     pinulongan
    -0.52
    Réalisation
    -0.51
    IsContent
    -0.50
    addPreferredGap
    -0.50
     locations
    -0.49
     الرياضيه
    -0.49
    POSITIVE LOGITS
    polazione
    0.60
    bestos
    0.59
    helial
    0.56
     oxidase
    0.56
    acterium
    0.55
    aphthalene
    0.55
    iotensin
    0.55
    oflavin
    0.52
    initComponents
    0.52
     carbonyl
    0.51
    Activations Density 0.012%

    No Known Activations