© 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. 97089
    Prev
    Next
    INDEX
    Explanations

    relative pronouns

    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
     adalah
    -0.75
     is
    -0.69
     was
    -0.68
     includes
    -0.67
     ialah
    -0.66
    าก็
    -0.65
     consists
    -0.61
     represents
    -0.61
     depends
    -0.60
     comprises
    -0.59
    POSITIVE LOGITS
     الحره
    0.60
    enumii
    0.59
     chré
    0.58
     Betrach
    0.57
    consulté
    0.57
    ècie
    0.56
    SystemColors
    0.56
     arşivlendi
    0.56
    enumi
    0.55
     démocr
    0.53
    Activations Density 0.004%

    No Known Activations