© 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. 4-CLT-HP
    7. 1073
    Prev
    Next
    INDEX
    Explanations

    to

    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
     replacing
    -0.54
    ніципалі
    -0.54
     EdgeInsets
    -0.54
    Rüyada
    -0.52
     distributing
    -0.51
    yente
    -0.51
     overtaking
    -0.48
    replacing
    -0.47
    Substitute
    -0.46
     Replacing
    -0.46
    POSITIVE LOGITS
     createState
    0.66
     purpoſe
    0.66
     SwitchCompat
    0.62
    ItemBackground
    0.59
    ंदीखरीदारी
    0.58
     pleaſure
    0.57
     Chrift
    0.55
     Monfieur
    0.54
    IsContent
    0.53
     Jefus
    0.52
    Activations Density 0.008%

    No Known Activations