© 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. 4-CLT-HP
    7. 4974
    Prev
    Next
    INDEX
    Explanations

    Trick

    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
    PasswordEncoder
    -0.58
    DockStyle
    -0.56
    TagMode
    -0.54
     calendriers
    -0.54
    XmlAccessType
    -0.54
     LoginComponent
    -0.54
    Datuak
    -0.52
    TagHelper
    -0.52
    partimento
    -0.52
    enumi
    -0.51
    POSITIVE LOGITS
     e
    0.89
     this
    0.82
     i
    0.82
    this
    0.73
     for
    0.68
     such
    0.66
    Including
    0.65
     ie
    0.65
     Again
    0.63
     especially
    0.61
    Activations Density 0.001%

    No Known Activations