© 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. 4926
    Prev
    Next
    INDEX
    Explanations

    the role of

    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
    mtable
    -0.63
     contextLoads
    -0.60
    findpost
    -0.58
    endcsname
    -0.54
    ScopeManager
    -0.53
    WriteTagHelper
    -0.53
     tenté
    -0.52
    KommentareTeilen
    -0.50
    ANTLR
    -0.50
     viewDidLoad
    -0.50
    POSITIVE LOGITS
     the
    0.61
     values
    0.57
     threat
    0.57
     witnesses
    0.48
     critics
    0.48
     reason
    0.47
    BufferException
    0.47
    LayoutConstraint
    0.47
     transférez
    0.46
     power
    0.45
    Activations Density 0.001%

    No Known Activations