© 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. 91575
    Prev
    Next
    INDEX
    Explanations

    seed

    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
    jspx
    -0.56
    verwijspagina
    -0.52
    \}^{
    -0.50
    ))[
    -0.47
    UserScript
    -0.46
     prochaines
    -0.46
    ...");
    -0.46
     bandeira
    -0.46
    yield
    -0.45
    ôi
    -0.44
    POSITIVE LOGITS
    ConstraintMaker
    0.63
    bietern
    0.59
     friends
    0.59
    AutoresizingMask
    0.59
     teammates
    0.56
     MOP
    0.56
     Betis
    0.54
    Obrázky
    0.54
    friends
    0.54
    BufferException
    0.53
    Activations Density 0.001%

    No Known Activations