© 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. 1590
    Prev
    Next
    INDEX
    Explanations

    the

    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
     consultato
    -0.91
     '\\;'
    -0.75
     الحره
    -0.73
    complexContent
    -0.73
    MigrationBuilder
    -0.71
     laſt
    -0.70
     behulp
    -0.68
     beſt
    -0.66
     Theſe
    -0.66
     tantôt
    -0.66
    POSITIVE LOGITS
    esgue
    0.53
      (
    0.50
     A
    0.48
     massive
    0.48
    romolecules
    0.47
    okin
    0.45
    targeting
    0.45
    meisters
    0.45
    TRIES
    0.44
    LEAR
    0.43
    Activations Density 0.001%

    No Known Activations