© 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. 76083
    Prev
    Next
    INDEX
    Explanations

    Random text/code

    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
    تقاوى
    -0.74
    GEBURTSDATUM
    -0.72
     виправивши
    -0.70
    LookAnd
    -0.68
    Datuak
    -0.66
     Италијани
    -0.66
    MigrationBuilder
    -0.66
     дописавши
    -0.64
     незавершена
    -0.63
     stresses
    -0.62
    POSITIVE LOGITS
    PhysRevLett
    0.40
     atacado
    0.40
    UserScript
    0.39
     ]);
    0.39
    gatsby
    0.37
     abiertos
    0.37
    bitField
    0.36
    StreamReader
    0.35
     ]
    0.35
     löyty
    0.35
    Activations Density 0.000%

    No Known Activations