© 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. 1-CLT-HP
    7. 13787
    Prev
    Next
    INDEX
    Explanations

    code and libraries

    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
    aliere
    -0.49
    zu
    -0.47
    ial
    -0.45
    éndolo
    -0.45
    AxisAlignment
    -0.42
    しに
    -0.41
    éndole
    -0.40
    尽
    -0.38
    databind
    -0.38
    NÉ
    -0.38
    POSITIVE LOGITS
    featureID
    0.93
     initComponents
    0.85
     ostavi
    0.85
     <>",
    0.84
    JspWriter
    0.81
     chofe
    0.80
     itſelf
    0.79
    parsedMessage
    0.79
     дописавши
    0.79
     فريبيس
    0.79
    Activations Density 0.052%

    No Known Activations