© 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. 4916
    Prev
    Next
    INDEX
    Explanations

    official procedures/applications

    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
     مشين
    -0.87
    parsedMessage
    -0.74
     étoient
    -0.74
    awaiter
    -0.73
    Diwedd
    -0.73
     feroit
    -0.71
    ItemBackground
    -0.71
    SourceChecksum
    -0.71
     Roskov
    -0.70
     hâte
    -0.68
    POSITIVE LOGITS
     observation
    0.45
     Agency
    0.45
    dura
    0.44
     agency
    0.43
     qu
    0.41
    thalle
    0.41
     Los
    0.40
    ái
    0.40
     atti
    0.40
     alber
    0.40
    Activations Density 0.001%

    No Known Activations