© 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. 2784
    Prev
    Next
    INDEX
    Explanations

    technical documentation/code/reviews

    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
    TagMode
    -0.73
    OGND
    -0.73
     ujednoznacz
    -0.70
    GEBURTSDATUM
    -0.69
    SOUNDBITE
    -0.69
    featureID
    -0.65
    esModule
    -0.64
    ValueStyle
    -0.62
    +#+#
    -0.60
    contentLoaded
    -0.60
    POSITIVE LOGITS
     the
    0.58
    olische
    0.52
    older
    0.47
     préfé
    0.44
    donor
    0.44
    Dat
    0.43
     donor
    0.43
     young
    0.43
    ที
    0.43
    QLabel
    0.41
    Activations Density 0.001%

    No Known Activations