© 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. 90877
    Prev
    Next
    INDEX
    Explanations

    hydraulic or anglo

    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
     <<<<<<<<<<<<<<
    -0.72
    RTEX
    -0.71
    قایناق‌لار
    -0.71
     démocr
    -0.69
    athy
    -0.68
    RegistryLite
    -0.66
     invokingState
    -0.66
     RIPRODUZIONE
    -0.65
     Longueur
    -0.64
     définiti
    -0.64
    POSITIVE LOGITS
    AccessorTable
    0.57
    这就
    0.54
    TagMode
    0.50
    [])
    0.50
    Dentro
    0.49
    ³)
    0.48
    numerusform
    0.47
    PHS
    0.47
    uxxxx
    0.46
    cinia
    0.46
    Activations Density 0.043%

    No Known Activations