© 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. 4-CLT-HP
    7. 559
    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
    
    -0.68
     فريبيس
    -0.64
    +#+#
    -0.52
    osoba
    -0.51
    }],
    -0.48
    Diwedd
    -0.48
    PhysRev
    -0.46
     Every
    -0.46
     Each
    -0.45
    WebElementEntity
    -0.44
    POSITIVE LOGITS
     تضيفلها
    0.71
    AddTagHelper
    0.66
    DockStyle
    0.64
     up
    0.63
     varying
    0.60
    HtmlAttribute
    0.60
    SequentialGroup
    0.59
     unspecified
    0.57
     several
    0.56
    Geografi
    0.56
    Activations Density 0.003%

    No Known Activations