© 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. 42629
    Prev
    Next
    INDEX
    Explanations

    warranty

    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
     warranty
    -0.71
    etat
    -0.70
    amot
    -0.58
     patrimoine
    -0.57
     पास
    -0.56
    SBATCH
    -0.53
    RuntimeObject
    -0.50
     Warranty
    -0.49
     hongos
    -0.48
    own
    -0.48
    POSITIVE LOGITS
    <?
    0.67
    ')):
    0.64
    NameInMap
    0.59
     nahilalakip
    0.57
    tencent
    0.57
     calendriers
    0.55
    windowFixed
    0.55
    EndProject
    0.54
    (!__
    0.54
     هيا
    0.54
    Activations Density 0.280%

    No Known Activations