© 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. 5276
    Prev
    Next
    INDEX
    Explanations

    rules and instructions

    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
    Hochspringen
    -0.65
     linkovi
    -0.60
    UnsafeEnabled
    -0.57
    uxxxx
    -0.54
     Himself
    -0.54
     незавершена
    -0.52
    himself
    -0.51
    Yourself
    -0.50
     transfieras
    -0.48
    piac
    -0.48
    POSITIVE LOGITS
    ثيق
    0.56
    :✨
    0.55
     estekak
    0.50
    umerable
    0.49
     a
    0.49
    WithIOException
    0.48
    afat
    0.47
     the
    0.47
     Hyman
    0.47
     sanitarias
    0.46
    Activations Density 0.000%

    No Known Activations