© 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. 0-CLT-HP
    7. 94878
    Prev
    Next
    INDEX
    Explanations

    aceae

    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
    ent
    -1.14
    ents
    -1.06
    ENT
    -0.79
    entes
    -0.78
    ENTS
    -0.75
    ente
    -0.71
    entu
    -0.68
    ENTE
    -0.68
     ent
    -0.67
    entas
    -0.64
    POSITIVE LOGITS
    ISupport
    0.94
    Datuak
    0.90
    ViewImports
    0.88
     Shakspeare
    0.88
     дописавши
    0.87
     myſelf
    0.87
     Majefty
    0.86
    writeFieldEnd
    0.86
     Monfieur
    0.85
    \{\\
    0.84
    Activations Density 0.135%

    No Known Activations