© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2199
    Prev
    Next
    INDEX
    Explanations

    ines

    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
     houſe
    -0.52
    enty
    -0.52
     themſelves
    -0.50
    tagHelper
    -0.49
    ſelves
    -0.48
    </thead>
    -0.47
     occaf
    -0.47
     myſelf
    -0.47
     reaſon
    -0.46
     caufe
    -0.46
    POSITIVE LOGITS
    aarrggbb
    0.79
    CppMethod
    0.75
    ArgsConstructor
    0.73
    nodoc
    0.60
    IVEREF
    0.59
     Audiodateien
    0.59
    +#+#
    0.59
    ChromeDriver
    0.58
    PerformLayout
    0.57
    XmlAccessType
    0.56
    Activations Density 0.001%

    No Known Activations