© 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. 43035
    Prev
    Next
    INDEX
    Explanations

    result

    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
    apimachinery
    -0.66
    phosa
    -0.64
     medicines
    -0.60
    vartis
    -0.60
     tumors
    -0.57
     Insulin
    -0.56
    crollView
    -0.56
     IEA
    -0.55
     Medicines
    -0.55
     systemic
    -0.54
    POSITIVE LOGITS
    GEBURTSDATUM
    0.80
    StoryboardSegue
    0.64
    ClientSize
    0.58
    SharedCtor
    0.58
    ParallelGroup
    0.56
    featureID
    0.51
    BeginInit
    0.50
    HasIndex
    0.50
    AutoScaleMode
    0.48
    ględ
    0.48
    Activations Density 1.534%

    No Known Activations