© 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. 3207
    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
     MainAxisSize
    -0.58
    SPJ
    -0.55
    ATM
    -0.53
     PhpStorm
    -0.51
    Sno
    -0.50
     shove
    -0.50
     senators
    -0.49
    Obama
    -0.49
    até
    -0.49
    ########.
    -0.48
    POSITIVE LOGITS
     Administrativna
    0.64
    SourceChecksum
    0.53
     nahilalakip
    0.53
     RIPRODUZIONE
    0.51
     otomatig
    0.50
    lccn
    0.49
    Hozzá
    0.49
     agrí
    0.46
    Ингредиенты
    0.46
     resourceCulture
    0.45
    Activations Density 0.007%

    No Known Activations