© 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. 4-CLT-HP
    7. 1420
    Prev
    Next
    INDEX
    Explanations

    Whilst

    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
     entanto
    -0.59
     ser
    -0.50
    est
    -0.50
    esse
    -0.47
    }/
    -0.46
     nahilalakip
    -0.46
    oció
    -0.46
    🏻
    -0.46
    ++]
    -0.45
     ©️
    -0.45
    POSITIVE LOGITS
    uxxxx
    0.69
     MatDialog
    0.65
    CDCl
    0.60
     المعيارى
    0.58
     refugees
    0.58
     Bioaccumulative
    0.57
    ConstraintMaker
    0.56
    lafen
    0.56
     TextAppearance
    0.55
    adaptiveStyles
    0.54
    Activations Density 0.003%

    No Known Activations