© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93691
    Prev
    Next
    INDEX
    Explanations

    rate

    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
     مرئيه
    -0.59
    CopyWith
    -0.57
    :✨
    -0.54
    Portail
    -0.52
    MessageOf
    -0.51
     Савезне
    -0.51
     podjela
    -0.50
     Instability
    -0.50
    Datuak
    -0.47
    inghouse
    -0.46
    POSITIVE LOGITS
    ftagPool
    0.61
     seguido
    0.54
    ecore
    0.53
    Personendaten
    0.53
     חיצוניים
    0.50
     of
    0.49
    plist
    0.49
     становника
    0.49
     AttributeSet
    0.48
    Française
    0.48
    Activations Density 0.010%

    No Known Activations