© 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. 5-CLT-HP
    7. 97799
    Prev
    Next
    INDEX
    Explanations

    Technical and varied content

    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
     is
    -0.60
     will
    -0.54
     has
    -0.52
     continues
    -0.50
     attualmente
    -0.49
     becomes
    -0.49
     calore
    -0.48
     makes
    -0.47
     utilizz
    -0.47
     goes
    -0.47
    POSITIVE LOGITS
     ModelExpression
    1.02
     Platform
    0.85
     Model
    0.85
     يتيمه
    0.82
     виправивши
    0.82
     Kit
    0.81
     Chart
    0.81
     Site
    0.80
    ^(@)
    0.80
     Engine
    0.78
    Activations Density 0.047%

    No Known Activations