© 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. 91397
    Prev
    Next
    INDEX
    Explanations

    Temperature (Celsius)

    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
     فريبيس
    -0.63
    Diweddarwch
    -0.54
    <bos>
    -0.54
    balleur
    -0.50
     OMIT
    -0.49
    stuff
    -0.47
    олові
    -0.47
     Farming
    -0.44
     nahilalakip
    -0.44
    enciaga
    -0.44
    POSITIVE LOGITS
     
    0.65
    rozco
    0.58
     K
    0.58
     k
    0.57
    rę
    0.54
    Morfo
    0.54
    otek
    0.52
     independent
    0.51
    liothèque
    0.50
     وتسجيلات
    0.50
    Activations Density 0.020%

    No Known Activations