© 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. 0-CLT-HP
    7. 90526
    Prev
    Next
    INDEX
    Explanations

    "relates to"

    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
     
    -0.91
     a
    -0.75
     in
    -0.69
     de
    -0.66
     C
    -0.65
     B
    -0.65
     un
    -0.65
     E
    -0.65
     op
    -0.65
     O
    -0.64
    POSITIVE LOGITS
     myſelf
    1.88
     Efq
    1.86
     Theſe
    1.80
     Monfieur
    1.80
     itſelf
    1.76
    ſelf
    1.70
     iſt
    1.69
     themſelves
    1.68
     Jefus
    1.66
     pleaſure
    1.66
    Activations Density 2.450%

    No Known Activations