© 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. 5018
    Prev
    Next
    INDEX
    Explanations

    Taxonomy

    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
     
    -0.48
    agli
    -0.45
    landse
    -0.44
    ướ
    -0.41
    sert
    -0.41
     amb
    -0.41
    bule
    -0.40
     zum
    -0.40
     the
    -0.40
    　　《
    -0.40
    POSITIVE LOGITS
     InputDecoration
    0.84
    ########.
    0.80
     AttributeSet
    0.79
    Personensuche
    0.77
    setVerticalGroup
    0.73
     Normdatei
    0.73
    __(/*!
    0.72
    CppMethod
    0.71
    makeConstraints
    0.71
     AssemblyCulture
    0.70
    Activations Density 0.001%

    No Known Activations