© 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. 94391
    Prev
    Next
    INDEX
    Explanations

    Webpage/URL contents

    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
    abestanden
    -0.84
     []).
    -0.78
     Downloaded
    -0.77
     kasarigan
    -0.77
     Мексичка
    -0.72
    VersionUID
    -0.72
    DebuggerNonUser
    -0.72
    SharedDtor
    -0.72
    ChildScrollView
    -0.71
    Downloaded
    -0.69
    POSITIVE LOGITS
    setopt
    0.41
     offerts
    0.38
    svc
    0.35
     brevi
    0.35
     congi
    0.35
     corpi
    0.34
     imedi
    0.33
     beginnen
    0.33
    كم
    0.32
    izen
    0.32
    Activations Density 0.015%

    No Known Activations