© 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. 97490
    Prev
    Next
    INDEX
    Explanations

    this

    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
    key
    -0.48
     Especially
    -0.46
    ांक
    -0.44
     
    -0.43
     by
    -0.43
    WithValue
    -0.43
     especially
    -0.43
    Many
    -0.42
    many
    -0.42
     Many
    -0.42
    POSITIVE LOGITS
     Roskov
    1.16
    IsContent
    1.09
    GEBURTSDATUM
    1.06
    webElementXpaths
    1.04
    DeleteBehavior
    0.96
     autorytatywna
    0.96
    SharedDtor
    0.93
     propOrder
    0.93
    rungsseite
    0.92
    MessageOf
    0.92
    Activations Density 0.002%

    No Known Activations