© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2537
    Prev
    Next
    INDEX
    Explanations

    all

    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
     âmes
    -0.62
     vœux
    -0.60
     vérit
    -0.59
     propres
    -0.58
     kyse
    -0.57
     enfans
    -0.55
     preuves
    -0.54
     genoux
    -0.53
     particulières
    -0.53
     misura
    -0.52
    POSITIVE LOGITS
    tagHelperRunner
    0.79
    findpost
    0.76
     pinulongan
    0.75
     betweenstory
    0.74
     Normdatei
    0.74
    BindView
    0.73
    artifactId
    0.71
    featureID
    0.71
     ModelExpression
    0.68
     '\\;'
    0.68
    Activations Density 0.001%

    No Known Activations