© 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. 1-CLT-HP
    7. 14379
    Prev
    Next
    INDEX
    Explanations

    bley

    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
    bley
    -0.79
     to
    -0.47
     mon
    -0.45
     here
    -0.44
    ss
    -0.44
     old
    -0.44
     kola
    -0.43
     now
    -0.43
     current
    -0.43
     thought
    -0.41
    POSITIVE LOGITS
    NameInMap
    0.77
    setVerticalGroup
    0.71
    styleType
    0.69
     mergeFrom
    0.69
    Datuak
    0.67
     hObject
    0.67
     '\\;'
    0.65
    Obrázky
    0.65
     Wicidata
    0.65
     링크
    0.65
    Activations Density 0.417%

    No Known Activations