© 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. 98225
    Prev
    Next
    INDEX
    Explanations

    Cell division

    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
     resourceCulture
    -0.53
    ̀n
    -0.51
    peh
    -0.50
     Mah
    -0.49
     Maria
    -0.48
    XO
    -0.47
    fortawesome
    -0.45
    ψε
    -0.45
    prepareStatement
    -0.44
    wyneth
    -0.44
    POSITIVE LOGITS
    ftagPool
    0.73
    UpdateCommand
    0.62
     pleaſure
    0.62
     ſche
    0.60
    SBATCH
    0.57
    tvguidetime
    0.57
    licky
    0.57
    ✨:
    0.56
    ^(@)
    0.56
     checkpoint
    0.55
    Activations Density 0.003%

    No Known Activations