© 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. 4778
    Prev
    Next
    INDEX
    Explanations

    Body and environment

    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
     surrounding
    -0.81
     surroundings
    -0.59
     surround
    -0.59
     surrounds
    -0.57
     окружа
    -0.52
     entorno
    -0.51
    /*
    -0.50
    rounding
    -0.50
     вокруг
    -0.47
     sekitarnya
    -0.47
    POSITIVE LOGITS
    fjspx
    0.71
    Geplaatst
    0.70
    Hentet
    0.69
    +#+#
    0.69
     onCreateView
    0.68
    formik
    0.67
    Brainz
    0.66
    ніципалі
    0.64
    первых
    0.64
    setVerticalGroup
    0.63
    Activations Density 0.003%

    No Known Activations