© 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. 42885
    Prev
    Next
    INDEX
    Explanations

    scientific/medical research

    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
    Effectiveness
    -0.86
     Effectiveness
    -0.85
    ReusableCell
    -0.77
    effectiveness
    -0.73
    BASEPATH
    -0.72
    providedIn
    -0.72
     initComponents
    -0.69
    UrlResolution
    -0.69
    Einzelnachweise
    -0.68
    prepareStatement
    -0.68
    POSITIVE LOGITS
    hnia
    0.44
     Investigation
    0.42
    ly
    0.41
    utant
    0.40
    orylation
    0.39
    нюю
    0.39
     Buried
    0.39
     gondol
    0.39
     INVESTIGATION
    0.39
    ticism
    0.38
    Activations Density 1.310%

    No Known Activations