© 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. 4-CLT-HP
    7. 947
    Prev
    Next
    INDEX
    Explanations

    Punctuation and "the"

    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
    Abit
    -0.67
     ControllerBase
    -0.62
    Chham
    -0.62
     мәкал
    -0.62
    RetentionPolicy
    -0.61
    UserScript
    -0.60
    transQ
    -0.60
    Personensuche
    -0.59
    Datuak
    -0.59
    protoimpl
    -0.59
    POSITIVE LOGITS
    ﾟ
    0.53
     just
    0.51
     problems
    0.48
    liferay
    0.47
    '])->
    0.47
    rxjs
    0.47
    ])));
    0.46
    TagHelpers
    0.46
    ']}
    0.44
    ')):
    0.44
    Activations Density 0.001%

    No Known Activations