© 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. 42851
    Prev
    Next
    INDEX
    Explanations

    technical/vague use of "extreme"

    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
     Efq
    -1.15
     Monfieur
    -0.99
     mourut
    -0.95
     étoit
    -0.91
     myſelf
    -0.91
     auroit
    -0.88
    domestic
    -0.88
    Personensuche
    -0.86
     ferons
    -0.84
     noires
    -0.84
    POSITIVE LOGITS
    um
    0.56
    ity
    0.55
    ,
    0.54
    BeginInit
    0.53
    est
    0.51
     let
    0.51
    че
    0.50
    és
    0.49
     
    0.49
    ties
    0.48
    Activations Density 0.045%

    No Known Activations