© 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. 1-CLT-HP
    7. 9763
    Prev
    Next
    INDEX
    Explanations

    wind energy

    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
    AndEndTag
    -0.81
    تقاوى
    -0.81
    ValueStyle
    -0.80
     للاسماء
    -0.75
    SequentialGroup
    -0.71
    StructEnd
    -0.71
    LLocation
    -0.68
    Portale
    -0.67
    ImageContext
    -0.64
    setVerticalGroup
    -0.64
    POSITIVE LOGITS
    ThroughAttribute
    0.49
    modes
    0.44
    чнее
    0.42
    意思是
    0.41
    ]}>
    0.40
     aplican
    0.40
    quares
    0.40
     modes
    0.40
     plan
    0.40
    msubsup
    0.39
    Activations Density 0.014%

    No Known Activations