© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4097
    Prev
    Next
    INDEX
    Explanations

    is

    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
    :][
    -0.50
    Kindle
    -0.50
     worms
    -0.46
    RNAs
    -0.46
    ">+
    -0.45
     Wikimedijinoj
    -0.44
    PhysRevLett
    -0.44
     referenties
    -0.44
    worms
    -0.43
     UITextField
    -0.43
    POSITIVE LOGITS
     فريبيس
    0.63
     the
    0.62
     CreateTagHelper
    0.59
    ftagPool
    0.58
    Kanpo
    0.57
    called
    0.55
     keberadaan
    0.53
     Dr
    0.52
     titulares
    0.52
     CALLED
    0.52
    Activations Density 0.002%

    No Known Activations