© 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. 94212
    Prev
    Next
    INDEX
    Explanations

    processes, methods

    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
    Vidite
    -0.84
    webElementXpaths
    -0.73
    lapsingToolbar
    -0.70
    RegressionTest
    -0.65
    ✭✭
    -0.63
     dAtA
    -0.61
     methods
    -0.59
    entera
    -0.59
    THON
    -0.59
     various
    -0.58
    POSITIVE LOGITS
    them
    0.47
     _:
    0.46
     Improvement
    0.44
    ")[
    0.43
     Identification
    0.43
    !:
    0.42
     μαζί
    0.42
    :[
    0.41
     don
    0.40
    Beskrivelse
    0.40
    Activations Density 0.011%

    No Known Activations