© 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. 5-CLT-HP
    7. 94574
    Prev
    Next
    INDEX
    Explanations

    from

    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
    קישורים
    -0.69
     autorytatywna
    -0.60
     للمعارف
    -0.58
    ativement
    -0.57
    HtmlAttribute
    -0.56
     Numerade
    -0.54
     Réponses
    -0.53
     Italijani
    -0.52
     MenuView
    -0.52
    GenerationType
    -0.51
    POSITIVE LOGITS
    __':
    0.64
    AndEndTag
    0.62
     the
    0.57
     several
    0.56
     Normdatei
    0.56
    __':
    0.56
    BeginContext
    0.56
     two
    0.56
     projects
    0.53
     four
    0.52
    Activations Density 0.002%

    No Known Activations