© 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. 4-CLT-HP
    7. 640
    Prev
    Next
    INDEX
    Explanations

    land

    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
    ContentAsync
    -0.68
    IntoConstraints
    -0.68
    DoubleQuotes
    -0.67
    UnitTesting
    -0.63
    maakt
    -0.63
    __);
    -0.62
     CWE
    -0.60
    ]--;
    -0.60
    voerd
    -0.59
    mitian
    -0.59
    POSITIVE LOGITS
     وتسجيلات
    0.60
     оригіналу
    0.49
    transQ
    0.46
    IBOutlet
    0.44
    ion
    0.44
    Quite
    0.43
    ce
    0.42
     РС
    0.42
     anf
    0.41
    UnusedPrivate
    0.41
    Activations Density 0.003%

    No Known Activations