© 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. 5948
    Prev
    Next
    INDEX
    Explanations

    needs and requirements

    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
    onPause
    -0.46
     to
    -0.43
     celebration
    -0.39
     Savoy
    -0.37
     celebrate
    -0.36
    ToAction
    -0.36
    })->
    -0.35
     tc
    -0.35
    Confidential
    -0.35
    Entry
    -0.34
    POSITIVE LOGITS
    URLException
    0.80
    iastes
    0.78
     of
    0.77
    SourceChecksum
    0.76
    webElement
    0.74
    بوابة
    0.73
    OGND
    0.70
     насељу
    0.69
     CreateTagHelper
    0.68
     itſelf
    0.68
    Activations Density 0.001%

    No Known Activations