© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1802
    Prev
    Next
    INDEX
    Explanations

    inclusion

    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
     surla
    -0.76
    ']],
    -0.69
     CURIAM
    -0.69
    BeginInit
    -0.66
    TintMode
    -0.65
    Datuak
    -0.64
    — 
    -0.64
    EndInit
    -0.63
    }\]
    -0.63
    CPtr
    -0.62
    POSITIVE LOGITS
     to
    0.63
    frame
    0.55
    <bos>
    0.53
    Становништво
    0.51
    PEND
    0.51
     treatments
    0.50
    Last
    0.49
    leva
    0.48
     variations
    0.48
    /*
    0.48
    Activations Density 0.247%

    No Known Activations