© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 390
    Prev
    Next
    INDEX
    Explanations

    code/commands/application

    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
    Portail
    -0.72
     Roskov
    -0.60
    __':
    -0.56
    ільки
    -0.54
    سطس
    -0.53
     MCD
    -0.52
    moveToFirst
    -0.51
     '\\;'
    -0.50
    nastics
    -0.49
     endfor
    -0.49
    POSITIVE LOGITS
    XmlAccessorType
    0.63
     AssemblyCompany
    0.56
    pushFollow
    0.55
    findpost
    0.54
    YOND
    0.50
    complexContent
    0.50
    sizeCache
    0.49
    ⓧ
    0.49
     LoggerFactory
    0.47
     Newswire
    0.47
    Activations Density 0.000%

    No Known Activations