© 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. 5-CLT-HP
    7. 2572
    Prev
    Next
    INDEX
    Explanations

    denoting

    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
    MethodManager
    -0.57
    kuuta
    -0.44
    tagHelperRunner
    -0.44
     quoi
    -0.43
     Diplo
    -0.43
    what
    -0.41
     olio
    -0.41
     smrti
    -0.41
    oporosis
    -0.40
    IActionResult
    -0.40
    POSITIVE LOGITS
     AttributeSet
    0.65
    Rüyada
    0.62
    rungsseite
    0.58
     Erişim
    0.58
    parsedMessage
    0.57
    IonicModule
    0.57
    RTLR
    0.56
    FunctionFlags
    0.56
    gerufen
    0.55
    باشد
    0.55
    Activations Density 0.003%

    No Known Activations