© 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. 4-CLT-HP
    7. 2676
    Prev
    Next
    INDEX
    Explanations

    of

    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
     courbe
    -0.52
    .
    -0.51
     promozione
    -0.51
     and
    -0.48
     správ
    -0.48
     équilibre
    -0.47
     equilíbrio
    -0.47
    ,
    -0.46
    lack
    -0.44
     besten
    -0.44
    POSITIVE LOGITS
    aarrggbb
    0.73
     lenker
    0.69
    :✨
    0.68
    DrawerToggle
    0.68
     snippetHide
    0.67
     SwitchCompat
    0.67
    OptionsMenu
    0.67
    ########.
    0.66
    \{\\
    0.65
     alphabetically
    0.64
    Activations Density 0.005%

    No Known Activations