© 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. 0-CLT-HP
    7. 94803
    Prev
    Next
    INDEX
    Explanations

    IE

    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
    IE
    -0.95
    e
    -0.46
    liferay
    -0.45
    as
    -0.44
    ACE
    -0.44
    IC
    -0.43
     XMLHttpRequest
    -0.43
    he
    -0.43
    enthal
    -0.42
    on
    -0.40
    POSITIVE LOGITS
     purpoſe
    0.85
     betweenstory
    0.84
     ComVisible
    0.81
     pleaſure
    0.78
    تقاوى
    0.77
     '\\;'
    0.77
    vician
    0.76
     Anſ
    0.75
     nahilalakip
    0.75
     Reſ
    0.74
    Activations Density 0.118%

    No Known Activations