© 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. 420
    Prev
    Next
    INDEX
    Explanations

    Changes

    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
     yourself
    -0.55
    izarse
    -0.52
     Yourself
    -0.50
     slä
    -0.49
    VersionUID
    -0.49
     valido
    -0.47
    SuppressLint
    -0.46
     langsung
    -0.46
    эффици
    -0.45
    dank
    -0.45
    POSITIVE LOGITS
     the
    0.86
     their
    0.70
    makeConstraints
    0.62
    setVerticalGroup
    0.62
     parseFrom
    0.60
    Cyfeiriadau
    0.58
    Portail
    0.57
     OnTriggerEnter
    0.57
     getItemId
    0.57
     onOptions
    0.55
    Activations Density 0.004%

    No Known Activations