© 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. 0-CLT-HP
    7. 93513
    Prev
    Next
    INDEX
    Explanations

    far

    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
     far
    -1.10
    far
    -1.10
    Far
    -0.91
     Far
    -0.87
     FAR
    -0.81
    FAR
    -0.70
    ander
    -0.63
     E
    -0.56
     ne
    -0.55
     R
    -0.54
    POSITIVE LOGITS
     itſelf
    1.25
     myſelf
    1.20
     themſelves
    1.18
     himſelf
    1.17
     ſeveral
    1.16
     Monfieur
    1.16
     للمعارف
    1.14
    Geplaatst
    1.12
     Houſe
    1.08
     ſtate
    1.07
    Activations Density 0.093%

    No Known Activations