© 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. 0-CLT-HP
    7. 93243
    Prev
    Next
    INDEX
    Explanations

    flight or location

    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
     fly
    -1.00
     locate
    -0.68
     Fly
    -0.62
     locating
    -0.59
    Fly
    -0.50
    yntax
    -0.50
     Locate
    -0.48
     Manuscript
    -0.45
     k
    -0.45
     Sakit
    -0.45
    POSITIVE LOGITS
     betweenstory
    0.98
    ########.
    0.86
    脚注の使い方
    0.77
    ]")]
    0.66
    談社
    0.66
    Geplaatst
    0.62
    IntoConstraints
    0.61
     مرئيه
    0.61
    utilisons
    0.60
    WebElementEntity
    0.59
    Activations Density 1.656%

    No Known Activations