© 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. 93755
    Prev
    Next
    INDEX
    Explanations

    Software code/licenses

    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
    UnitTesting
    -0.67
    ագրություններ
    -0.53
     estimés
    -0.52
     ***!
    -0.49
    Aktualisiert
    -0.47
    unto
    -0.45
    .$$
    -0.44
     treating
    -0.44
     وصلة
    -0.44
    stu
    -0.44
    POSITIVE LOGITS
    WebElementEntity
    0.62
    ophan
    0.58
    omitempty
    0.52
    ProcessEvent
    0.51
     Yag
    0.50
    icitis
    0.50
    fohl
    0.50
    ýl
    0.49
    StringProperty
    0.49
     Région
    0.48
    Activations Density 0.006%

    No Known Activations