© 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. 91612
    Prev
    Next
    INDEX
    Explanations

    verb "to be"

    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
    <bos>
    -0.85
    UserScript
    -0.58
    )_/¯
    -0.55
    findpost
    -0.54
     poveznice
    -0.51
    ativement
    -0.50
     برانيه
    -0.49
    GEBURTS
    -0.49
    errHandler
    -0.49
     [*]
    -0.47
    POSITIVE LOGITS
    UnusedPrivate
    0.78
     Roskov
    0.67
     Majefty
    0.66
    fromnode
    0.61
     fevere
    0.58
     Cæsar
    0.57
     Houſe
    0.56
    DockStyle
    0.54
    BoxLayout
    0.54
    Erreferentziak
    0.54
    Activations Density 0.004%

    No Known Activations