© 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. 91320
    Prev
    Next
    INDEX
    Explanations

    Parenting and families

    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
    AccessorTable
    -0.62
     kasarigan
    -0.61
    gatsby
    -0.54
    SBATCH
    -0.53
    <bos>
    -0.52
    Distribuzione
    -0.52
    vaders
    -0.52
    delwed
    -0.51
    endgroup
    -0.50
    ChildScrollView
    -0.50
    POSITIVE LOGITS
    -
    0.71
     kysy
    0.67
     who
    0.63
     ilman
    0.55
     épaules
    0.55
     hyö
    0.54
     jorden
    0.54
     zucca
    0.53
     tarko
    0.52
     whose
    0.52
    Activations Density 0.000%

    No Known Activations