© 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. 92126
    Prev
    Next
    INDEX
    Explanations

    sale

    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
     mergeFrom
    -0.89
    ValueStyle
    -0.81
    Jeografia
    -0.79
     EconPapers
    -0.76
    +#+#
    -0.75
     Chwiliwch
    -0.75
     utafitiHapana
    -0.73
    ConstraintMaker
    -0.72
     AssemblyTitle
    -0.72
     kasarigan
    -0.71
    POSITIVE LOGITS
     of
    0.66
     number
    0.54
     saluti
    0.46
     No
    0.43
    ↵↵↵
    0.42
    Empty
    0.42
     further
    0.42
     دفع
    0.41
    ibili
    0.40
     Rail
    0.40
    Activations Density 0.015%

    No Known Activations