© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94067
    Prev
    Next
    INDEX
    Explanations

    offspring

    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
     offspring
    -1.12
     Италијани
    -1.10
     Parliament
    -1.04
     parliament
    -1.02
     Theſe
    -0.94
     '\\;'
    -0.89
     myſelf
    -0.88
    OGND
    -0.87
     himſelf
    -0.86
     themſelves
    -0.86
    POSITIVE LOGITS
    ing
    0.85
     for
    0.73
    ally
    0.63
     
    0.61
     a
    0.61
    um
    0.56
    ous
    0.56
    for
    0.55
    ries
    0.55
    ories
    0.54
    Activations Density 0.338%

    No Known Activations