© 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. 1-CLT-HP
    7. 46035
    Prev
    Next
    INDEX
    Explanations

    names

    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
    Бахар
    -0.47
     Ume
    -0.47
    Bson
    -0.46
    ANSAS
    -0.45
    Sponsor
    -0.45
    DOCTYPE
    -0.45
    DataAnnotations
    -0.45
     CHtml
    -0.44
     quotas
    -0.44
    otor
    -0.44
    POSITIVE LOGITS
     незавершена
    0.66
    >');
    0.65
     виправивши
    0.63
    verwijspagina
    0.61
     Савезне
    0.61
    EDEFAULT
    0.58
     الدولى
    0.57
    WriteTagHelper
    0.55
    ]--;
    0.55
    __':
    0.55
    Activations Density 0.172%

    No Known Activations