© 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. 0-CLT-HP
    7. 93138
    Prev
    Next
    INDEX
    Explanations

    question

    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
    íncia
    -0.46
    csolódó
    -0.46
     spese
    -0.45
    specialchars
    -0.44
    ttino
    -0.43
    inaison
    -0.42
     Noruega
    -0.41
     catalana
    -0.40
    кож
    -0.40
     of
    -0.39
    POSITIVE LOGITS
    findpost
    0.96
     Infórmanos
    0.94
    GEBURTSDATUM
    0.90
    queryInterface
    0.80
     <",
    0.76
    脚注の使い方
    0.75
    DebuggerNonUser
    0.74
    __).
    0.74
     AssemblyTitle
    0.73
     propOrder
    0.73
    Activations Density 0.060%

    No Known Activations