© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75657
    Prev
    Next
    INDEX
    Explanations

    trans

    np_max-act-logits · 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
    tagHelperRunner
    -0.81
     initComponents
    -0.79
     referenties
    -0.75
    Autoritní
    -0.75
    __":
    -0.71
     IBOutlet
    -0.66
    Personendaten
    -0.66
     vuitton
    -0.65
    ValueStyle
    -0.64
    ModelAdmin
    -0.64
    POSITIVE LOGITS
    pos
    0.50
     ret
    0.49
     res
    0.47
    loc
    0.43
    res
    0.42
    iting
    0.41
    wiki
    0.41
    formin
    0.39
    ester
    0.39
    FormTagHelper
    0.39
    Activations Density 0.007%

    No Known Activations