© 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. 95155
    Prev
    Next
    INDEX
    Explanations

    lite

    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
    ita
    -0.77
     (
    -0.65
    ,
    -0.64
    ite
    -0.62
     ben
    -0.61
     pri
    -0.60
     ha
    -0.60
     Test
    -0.60
    itas
    -0.59
     
    -0.59
    POSITIVE LOGITS
     itſelf
    1.84
     myſelf
    1.73
     Jefus
    1.68
     himſelf
    1.66
     Theſe
    1.62
     Houſe
    1.59
     Monfieur
    1.59
     Efq
    1.56
     pleaſure
    1.55
     houſe
    1.53
    Activations Density 0.179%

    No Known Activations