© 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. 46167
    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
    astu
    -0.46
    ettes
    -0.41
    ures
    -0.41
    s
    -0.40
    سبة
    -0.40
    ों
    -0.39
    ast
    -0.39
     FIL
    -0.39
    alt
    -0.38
    lt
    -0.38
    POSITIVE LOGITS
     InputDecoration
    0.79
    \{\\
    0.79
     noDo
    0.73
    rungsseite
    0.73
    OGND
    0.72
     defaultstate
    0.72
     HttpHeaders
    0.70
     المعيارى
    0.69
    <?
    0.68
     insuffisamment
    0.68
    Activations Density 0.005%

    No Known Activations