© 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. 43066
    Prev
    Next
    INDEX
    Explanations

    tries

    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
     تضيفلها
    -0.86
    Geplaatst
    -0.84
     moves
    -0.81
     commits
    -0.80
     carries
    -0.79
    ⓧ
    -0.76
     tackles
    -0.74
    moves
    -0.73
     Tries
    -0.73
    #+#
    -0.73
    POSITIVE LOGITS
    cookieParser
    0.52
     adelante
    0.48
    sog
    0.45
     Sog
    0.45
    BrowserModule
    0.45
    getActiveSheet
    0.45
     effec
    0.44
     effectively
    0.43
    NullCheck
    0.43
     us
    0.43
    Activations Density 1.754%

    No Known Activations