© 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. 0-CLT-HP
    7. 1571
    Prev
    Next
    INDEX
    Explanations

    typo

    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
    SerializedSize
    -0.73
     BF
    -0.70
    lessly
    -0.69
    ScopeManager
    -0.69
    MessageState
    -0.67
    ly
    -0.65
    elan
    -0.65
     arbitrage
    -0.64
    lessness
    -0.64
    lish
    -0.62
    POSITIVE LOGITS
    مصادر
    0.53
    Personensuche
    0.49
    ագրություններ
    0.49
    InstanceState
    0.47
    ftagPool
    0.47
    setObjectName
    0.46
     يتيمه
    0.46
     planas
    0.46
    ```
    0.43
     typelib
    0.42
    Activations Density 0.246%

    No Known Activations