© 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. 0-CLT-HP
    7. 93999
    Prev
    Next
    INDEX
    Explanations

    location and containment

    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
     inside
    -1.27
     within
    -1.19
    within
    -1.06
    Within
    -1.06
    inside
    -1.04
     внутри
    -0.98
     dentro
    -0.98
     WITHIN
    -0.97
    Inside
    -0.96
     dedans
    -0.96
    POSITIVE LOGITS
     the
    1.09
     a
    0.89
     your
    0.69
     an
    0.68
     our
    0.67
     some
    0.66
     of
    0.66
     their
    0.66
     these
    0.63
     its
    0.61
    Activations Density 0.096%

    No Known Activations