© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73518
    Prev
    Next
    INDEX
    Explanations

    separators

    np_max-act-logits · 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
     مرئيه
    -0.47
    ?')
    -0.43
    ंदीखरीदारी
    -0.43
    +#+#
    -0.42
    WebVitals
    -0.42
    東洋
    -0.42
     Honour
    -0.41
     IBOutlet
    -0.40
     Tinker
    -0.40
    Према
    -0.40
    POSITIVE LOGITS
    出版年
    0.82
     sy
    0.59
    matchCondition
    0.57
    ··
    0.55
     ***!
    0.55
    TabIndex
    0.54
    وفة
    0.53
     pilo
    0.53
    nodoc
    0.53
     незавершена
    0.52
    Activations Density 0.001%

    No Known Activations