© 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. 3799
    Prev
    Next
    INDEX
    Explanations

    the

    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
     RequestMethod
    -0.46
     
    -0.45
     a
    -0.45
     aDecoder
    -0.44
     Jod
    -0.44
    FromArgb
    -0.43
    schild
    -0.42
     PropertyChanged
    -0.42
    Schedulers
    -0.42
     carefully
    -0.42
    POSITIVE LOGITS
    GEBURTSDATUM
    0.75
    abestanden
    0.74
    XmlAccessorType
    0.72
    RegressionTest
    0.71
     CURIAM
    0.69
    исленность
    0.65
    LookAnd
    0.60
    ConstraintMaker
    0.60
    IndentedString
    0.59
    Personendaten
    0.58
    Activations Density 0.002%

    No Known Activations