© 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. 97349
    Prev
    Next
    INDEX
    Explanations

    Numerical, location, research data

    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
    \{\\
    -0.73
     fl
    -0.63
    .'”
    -0.60
    ."]
    -0.57
     IRIS
    -0.57
    ſelves
    -0.56
     ?'
    -0.56
     MMC
    -0.55
     GLC
    -0.54
     transl
    -0.54
    POSITIVE LOGITS
     AssemblyCulture
    0.61
     religieuses
    0.59
    protoimpl
    0.59
     démocr
    0.54
     vectorielles
    0.53
    Còn
    0.53
    stateProvider
    0.52
     sauvages
    0.52
     ويكيپيديا
    0.52
     publicités
    0.51
    Activations Density 0.025%

    No Known Activations