© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2119
    Prev
    Next
    INDEX
    Explanations

    should

    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
     vectorielles
    -0.48
    instancetype
    -0.47
    apimachinery
    -0.47
    ">//
    -0.46
     Furthermore
    -0.46
     المعيارى
    -0.41
    乓
    -0.40
    Furthermore
    -0.39
    värr
    -0.39
     calendriers
    -0.39
    POSITIVE LOGITS
    wolves
    0.68
    pples
    0.68
    thmus
    0.68
    standers
    0.67
    teps
    0.65
    ductors
    0.65
    ibly
    0.64
    antly
    0.63
    orses
    0.63
    lably
    0.63
    Activations Density 0.002%

    No Known Activations