© 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. 93472
    Prev
    Next
    INDEX
    Explanations

    to

    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
    sendRedirect
    -0.47
    /*
    -0.44
    Até
    -0.44
    śmy
    -0.44
    HEP
    -0.42
    ORPG
    -0.41
    umers
    -0.40
    ikor
    -0.40
    Discography
    -0.39
    orexia
    -0.39
    POSITIVE LOGITS
    UnusedPrivate
    0.88
    parsedMessage
    0.80
    ViewById
    0.77
    LookAnd
    0.77
     تضيفلها
    0.74
     CreateTagHelper
    0.74
    DebuggerNonUser
    0.72
    WithIOException
    0.68
    MessageOf
    0.68
     AssemblyVersion
    0.68
    Activations Density 0.005%

    No Known Activations