© 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. 1-CLT-HP
    7. 9444
    Prev
    Next
    INDEX
    Explanations

    reckoned

    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
     Reef
    -0.49
     espagne
    -0.48
     Espagne
    -0.47
    mtd
    -0.47
    testng
    -0.47
    Espagne
    -0.46
     portugu
    -0.46
    rinos
    -0.45
    ασ
    -0.45
    rino
    -0.45
    POSITIVE LOGITS
    OGND
    0.93
    ⓧ
    0.80
    y
    0.67
    StructEnd
    0.63
    TargetException
    0.62
     Audiodateien
    0.61
    wieś
    0.60
    IsContent
    0.59
     تضيفلها
    0.59
    Personendaten
    0.58
    Activations Density 0.009%

    No Known Activations