© 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. 4828
    Prev
    Next
    INDEX
    Explanations

    out

    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
    WriteTagHelper
    -0.73
     оригіналу
    -0.72
    AndEndTag
    -0.70
    SharedDtor
    -0.69
    IsContent
    -0.68
     dalamnya
    -0.68
    DebuggerNonUser
    -0.66
    sizeCache
    -0.64
    antaranya
    -0.62
    raszam
    -0.62
    POSITIVE LOGITS
     Reverso
    0.51
     Heights
    0.49
     Off
    0.48
     realised
    0.47
    cyklo
    0.46
     reik
    0.46
    dze
    0.44
    QObject
    0.44
    fucker
    0.44
    mites
    0.44
    Activations Density 0.002%

    No Known Activations