© 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. 4741
    Prev
    Next
    INDEX
    Explanations

    explanation/clarification

    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
     صوتيه
    -0.57
    <bos>
    -0.55
    AccessorTable
    -0.54
    ondre
    -0.54
    XMLSchema
    -0.54
    slidesPer
    -0.52
     AssemblyTitle
    -0.51
    GOTREF
    -0.50
     فريبيس
    -0.49
    ecuted
    -0.49
    POSITIVE LOGITS
     here
    0.62
    NegativeButton
    0.58
    here
    0.55
     once
    0.51
    Here
    0.50
    λίου
    0.48
     Here
    0.48
     uintptr
    0.47
     revisited
    0.47
    Amérique
    0.47
    Activations Density 0.003%

    No Known Activations