© 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. 93814
    Prev
    Next
    INDEX
    Explanations

    arguments/opinions

    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
     flesta
    -0.52
    oa̍t
    -0.52
    deserved
    -0.47
     fleste
    -0.47
    produzione
    -0.47
    OGN
    -0.45
    lowe
    -0.44
     reputación
    -0.44
    lindungan
    -0.43
     redan
    -0.43
    POSITIVE LOGITS
    MLLoader
    0.93
    parsedMessage
    0.86
     CreateTagHelper
    0.86
     resourceCulture
    0.80
     onCancelled
    0.79
     ArrayAdapter
    0.78
    XmlAccessorType
    0.75
    Personendaten
    0.75
     onAnimation
    0.75
    MessageOf
    0.71
    Activations Density 0.029%

    No Known Activations