© 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. 0-CLT-HP
    7. 42744
    Prev
    Next
    INDEX
    Explanations

    Slowly

    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
    Slowly
    -0.94
     Slowly
    -0.82
    slowly
    -0.82
     slowly
    -0.81
     gradually
    -0.71
    ")]
    -0.71
     gradual
    -0.69
    }`;
    -0.68
    })`
    -0.68
    )]
    -0.68
    POSITIVE LOGITS
     nodig
    0.55
     estekak
    0.54
     gambe
    0.53
    kozás
    0.52
    ancang
    0.52
     démission
    0.52
     demikian
    0.50
    NameInMap
    0.50
     igualmente
    0.48
     cervello
    0.48
    Activations Density 0.187%

    No Known Activations