© 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. 20-CLT-HP
    7. 72783
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    uxxxx
    -0.66
     AssemblyTitle
    -0.66
     незавершена
    -0.65
    UnsafeEnabled
    -0.63
    ORAL
    -0.61
    ঠ
    -0.61
     typelib
    -0.60
    DotNetBar
    -0.59
     nakalista
    -0.59
    ///</
    -0.59
    POSITIVE LOGITS
    hashtags
    0.40
     pimienta
    0.39
    TableField
    0.39
    Ki
    0.38
     reembolso
    0.37
    SPATH
    0.37
    passt
    0.37
     tanım
    0.36
    Jerry
    0.35
    ť
    0.35
    Activations Density 0.002%

    No Known Activations