© 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. 1-CLT-HP
    7. 680
    Prev
    Next
    INDEX
    Explanations

    Neutr

    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
    SharedCtor
    -0.79
    AxisAlignment
    -0.73
     invokingState
    -0.71
     صوتيه
    -0.69
    SuccessListener
    -0.68
     newBuilder
    -0.66
     pinulongan
    -0.65
    WebServlet
    -0.65
     saites
    -0.65
    bootstrapcdn
    -0.63
    POSITIVE LOGITS
    azo
    0.47
     Conserv
    0.47
    a
    0.46
     magis
    0.46
    A
    0.44
     haast
    0.44
    az
    0.43
    put
    0.42
    Clar
    0.42
    puter
    0.41
    Activations Density 0.010%

    No Known Activations