© 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. 91775
    Prev
    Next
    INDEX
    Explanations

    Jesus

    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
    +#+
    -0.55
    abstractmethod
    -0.55
    ArgumentParser
    -0.51
    EDAD
    -0.50
    trab
    -0.49
    Gemeinsame
    -0.48
    tedrale
    -0.47
     Breite
    -0.47
    att
    -0.47
    dataclass
    -0.47
    POSITIVE LOGITS
    ErrorListener
    0.65
     AssemblyCompany
    0.64
    webElementXpaths
    0.60
    UnsafeEnabled
    0.58
    StateList
    0.56
    ChildScrollView
    0.56
     Réponses
    0.55
     '\\;'
    0.54
    tagHelperRunner
    0.54
    DockStyle
    0.52
    Activations Density 0.002%

    No Known Activations