© 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. 5-CLT-HP
    7. 5614
    Prev
    Next
    INDEX
    Explanations

    code/XML

    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
     المعيارى
    -0.67
    setVerticalGroup
    -0.66
    ButterKnife
    -0.54
    DockStyle
    -0.50
    íritu
    -0.49
    ChildScrollView
    -0.49
    脚注の使い方
    -0.49
    \{\\
    -0.48
     preparazione
    -0.47
    ísica
    -0.46
    POSITIVE LOGITS
     Roskov
    0.75
    Становништво
    0.62
     Wanderers
    0.60
     Arrivals
    0.59
     defaultstate
    0.58
     TestBed
    0.57
     насељу
    0.57
     raff
    0.56
     kasarigan
    0.55
     arrivals
    0.55
    Activations Density 0.003%

    No Known Activations