© 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. 0-CLT-HP
    7. 97059
    Prev
    Next
    INDEX
    Explanations

    ango

    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
    脚注の使い方
    -0.85
     resourceCulture
    -0.84
    featureID
    -0.80
    ValueStyle
    -0.79
    ThroughAttribute
    -0.78
    verwijspagina
    -0.75
    mybatisplus
    -0.75
     InputDecoration
    -0.75
    ագրություններ
    -0.74
    casian
    -0.72
    POSITIVE LOGITS
     prøve
    0.41
     Road
    0.40
    Road
    0.40
    spective
    0.39
     labores
    0.38
     O
    0.37
    ільки
    0.37
    loving
    0.36
     berdiri
    0.36
    ideae
    0.36
    Activations Density 0.148%

    No Known Activations