© 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. 4-CLT-HP
    7. 2338
    Prev
    Next
    INDEX
    Explanations

    the

    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
     onOptions
    -0.79
    XmlAccessorType
    -0.71
    MethodManager
    -0.70
    ModelSerializer
    -0.69
    IntoConstraints
    -0.67
     étoit
    -0.66
    DOCTYPE
    -0.66
    WriteTagHelper
    -0.66
    makeConstraints
    -0.65
    UnusedPrivate
    -0.65
    POSITIVE LOGITS
     Then
    0.51
     So
    0.49
     Hope
    0.48
     so
    0.47
     known
    0.47
     Crime
    0.46
    thenReturn
    0.46
    <eos>
    0.45
     Now
    0.44
    umably
    0.44
    Activations Density 0.006%

    No Known Activations