© 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. 90637
    Prev
    Next
    INDEX
    Explanations

    on

    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
     to
    -0.67
     for
    -0.58
     not
    -0.57
     all
    -0.55
     as
    -0.54
    -
    -0.54
     with
    -0.52
     I
    -0.51
     at
    -0.47
     into
    -0.47
    POSITIVE LOGITS
     itſelf
    1.21
     $_(
    1.11
     Houſe
    1.11
     Monfieur
    1.10
    \{\\
    1.09
     myſelf
    1.06
     themſelves
    1.05
     Cæsar
    1.03
     pleaſure
    1.03
     doubtnut
    1.02
    Activations Density 0.093%

    No Known Activations