© 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. 42810
    Prev
    Next
    INDEX
    Explanations

    ever already

    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
     already
    -0.84
    Already
    -0.75
    already
    -0.72
     Already
    -0.71
     redan
    -0.69
     ohnehin
    -0.66
     allá
    -0.65
     ALREADY
    -0.65
     allerede
    -0.65
    ALREADY
    -0.62
    POSITIVE LOGITS
    RegressionTest
    0.57
     acted
    0.57
     spent
    0.57
     died
    0.56
    RTEE
    0.56
     createState
    0.55
     been
    0.54
    <bos>
    0.53
    KURZBESCHREIBUNG
    0.53
     traveled
    0.52
    Activations Density 0.216%

    No Known Activations