© 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. 42888
    Prev
    Next
    INDEX
    Explanations

    had

    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
    its
    -0.88
    Its
    -0.85
     Its
    -0.69
     Itself
    -0.68
    itself
    -0.68
     kanyang
    -0.64
     itself
    -0.62
     côtés
    -0.60
     lèvres
    -0.60
     dépens
    -0.59
    POSITIVE LOGITS
     reads
    0.71
     catches
    0.71
    \{\\
    0.67
     }}"></
    0.67
     gains
    0.66
    qrstuvwxyz
    0.66
     floats
    0.65
    rophes
    0.65
     a
    0.64
     your
    0.64
    Activations Density 0.220%

    No Known Activations