© 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. 95345
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
     to
    -0.56
    ต์
    -0.51
    اولة
    -0.47
     '
    -0.47
    wij
    -0.47
     par
    -0.46
     kon
    -0.45
     (
    -0.44
     mu
    -0.44
     Kon
    -0.44
    POSITIVE LOGITS
    parsedMessage
    0.99
     Roskov
    0.99
    RegressionTest
    0.98
     feroit
    0.81
    ]='\
    0.80
     auroit
    0.79
     étoit
    0.78
    IsContent
    0.78
     termica
    0.78
    __':
    0.76
    Activations Density 0.364%

    No Known Activations