© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94035
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     so
    -0.49
     P
    -0.48
    ji
    -0.47
     O
    -0.47
    ic
    -0.46
     le
    -0.46
     «
    -0.45
    med
    -0.45
     leksikon
    -0.45
     em
    -0.44
    POSITIVE LOGITS
     itſelf
    0.94
     Efq
    0.88
     avoient
    0.86
     étoient
    0.84
     myſelf
    0.81
     détru
    0.81
    MENAFN
    0.79
     themſelves
    0.79
     poffible
    0.78
     métallique
    0.78
    Activations Density 0.007%

    No Known Activations