© 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. 5-CLT-HP
    7. 97629
    Prev
    Next
    INDEX
    Explanations

    opinions/arguments

    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
     avoient
    -0.63
    TypedDataSet
    -0.62
    EndContext
    -0.59
     kaynağından
    -0.57
     rightfully
    -0.57
    abstractmethod
    -0.55
     riconoscimento
    -0.54
    发表于
    -0.54
    Configurer
    -0.54
     focuses
    -0.52
    POSITIVE LOGITS
    JsonHelper
    0.55
    Respectfully
    0.55
    "?>
    0.55
    ématiques
    0.54
    MLLoader
    0.54
    Ծանոթ
    0.52
    (||
    0.48
    juries
    0.47
     pire
    0.47
     oddly
    0.46
    Activations Density 0.002%

    No Known Activations