© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4459
    Prev
    Next
    INDEX
    Explanations

    forum/tutorial content

    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
    StructEnd
    -0.53
     חיצוניים
    -0.51
     służ
    -0.47
     courriel
    -0.46
    GetAxis
    -0.46
    SearchView
    -0.45
    oneofs
    -0.45
    ầng
    -0.44
    msgTypes
    -0.44
    Personendaten
    -0.43
    POSITIVE LOGITS
     committing
    0.61
    makeText
    0.57
     planning
    0.57
    ArgumentParser
    0.55
     commit
    0.53
    PreferredItem
    0.53
    ategy
    0.52
    aronder
    0.52
     cooking
    0.50
     ""],
    0.50
    Activations Density 0.000%

    No Known Activations