© 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. 5-CLT-HP
    7. 93772
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    ềm
    -0.45
     forKey
    -0.42
     untuk
    -0.42
     jangka
    -0.41
     to
    -0.41
    ümü
    -0.40
     Kedua
    -0.40
    來自
    -0.40
    Gran
    -0.40
     suis
    -0.38
    POSITIVE LOGITS
     ModelExpression
    0.99
     like
    0.91
     يتيمه
    0.82
    /**
    0.75
    Personendaten
    0.70
    tagext
    0.66
    CloseOperation
    0.66
     MainAxisSize
    0.66
    ⓘ
    0.62
     Abp
    0.60
    Activations Density 0.000%

    No Known Activations