© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3485
    Prev
    Next
    INDEX
    Explanations

    Code and technical documentation

    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
     Fatima
    -0.77
    setVerticalGroup
    -0.72
     AttributeSet
    -0.65
    +#+#
    -0.61
     AssemblyVersion
    -0.59
    __':
    -0.58
     autorytatywna
    -0.57
    QMetaType
    -0.57
     ffilmiau
    -0.56
    Jeografia
    -0.55
    POSITIVE LOGITS
     useAppContext
    0.54
    hoga
    0.47
     ganglia
    0.43
     medulla
    0.42
    RectangleBorder
    0.40
     moulds
    0.39
    criminal
    0.39
    igshid
    0.39
     ganglion
    0.39
    CIUDAD
    0.39
    Activations Density 0.001%

    No Known Activations