© 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. 45832
    Prev
    Next
    INDEX
    Explanations

    kit

    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
    úly
    -0.53
     Falla
    -0.50
    UrlResolution
    -0.48
    циали
    -0.48
     entsch
    -0.47
     Parry
    -0.46
    pacho
    -0.46
    omock
    -0.45
     væ
    -0.45
    ennis
    -0.45
    POSITIVE LOGITS
    脚注の使い方
    0.64
    OrNil
    0.63
    onAttach
    0.63
     typelib
    0.59
     doInBackground
    0.59
    انيف
    0.57
     חיצוניים
    0.55
    HostException
    0.54
    BeginContext
    0.54
    PerformLayout
    0.54
    Activations Density 0.225%

    No Known Activations