© 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. 98086
    Prev
    Next
    INDEX
    Explanations

    (

    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
    :✨
    -0.75
     그리고
    -0.71
     and
    -0.68
     oprot
    -0.60
    FunctionFlags
    -0.59
    protoimpl
    -0.57
    そして
    -0.57
     Référence
    -0.57
     jsPsych
    -0.55
    )++;
    -0.55
    POSITIVE LOGITS
     BoxFit
    0.50
    for
    0.47
    expandindo
    0.46
    onOptions
    0.44
    дости
    0.44
    """,
    0.42
     to
    0.41
     for
    0.41
     MonoBehaviour
    0.40
    setPreferred
    0.40
    Activations Density 0.015%

    No Known Activations