© 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. 4545
    Prev
    Next
    INDEX
    Explanations

    You

    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
     تضيفلها
    -0.69
    MemoryWarning
    -0.61
    ReusableCell
    -0.59
    ylvania
    -0.58
     Signalez
    -0.58
    InSection
    -0.57
     विश्वसनीयता
    -0.55
    dshaw
    -0.55
     seh
    -0.55
    gesteld
    -0.54
    POSITIVE LOGITS
    this
    0.60
     this
    0.56
    DispatchToProps
    0.52
     tutte
    0.47
    addCriterion
    0.47
    iastes
    0.47
    AndEndTag
    0.47
    VIAF
    0.46
    Abp
    0.45
    ActionCreators
    0.45
    Activations Density 0.001%

    No Known Activations