© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43809
    Prev
    Next
    INDEX
    Explanations

    hurricanes

    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
    Tikang
    -0.85
    󠁿
    -0.85
     Cæsar
    -0.84
    Genetic
    -0.82
    MigrationBuilder
    -0.82
     Genetic
    -0.82
    Personensuche
    -0.82
    WriteTagHelper
    -0.81
     itſelf
    -0.79
    ducers
    -0.79
    POSITIVE LOGITS
    memberof
    0.51
    件事情
    0.48
    #+#
    0.46
     “
    0.45
     er
    0.45
     "
    0.42
     poter
    0.40
     der
    0.39
     tan
    0.38
     test
    0.37
    Activations Density 0.255%

    No Known Activations