© 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. 1851
    Prev
    Next
    INDEX
    Explanations

    groups/organizations

    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
     myſelf
    -0.61
     Frida
    -0.59
    OfThe
    -0.59
    NOPQRST
    -0.59
     reaſon
    -0.57
     Monfieur
    -0.57
    LookAnd
    -0.56
    lasty
    -0.54
     Hannes
    -0.54
     محفوظة
    -0.54
    POSITIVE LOGITS
     or
    0.60
     StatefulWidget
    0.55
    GraphicsUnit
    0.49
     like
    0.49
    SizeF
    0.48
    ,
    0.46
    jenih
    0.45
     and
    0.45
     cuerda
    0.44
     in
    0.44
    Activations Density 0.000%

    No Known Activations