© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77145
    Prev
    Next
    INDEX
    Explanations

    gas

    np_max-act-logits · 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
    Geplaatst
    -0.79
    andExpect
    -0.64
     Wikimedijinoj
    -0.60
     betweenstory
    -0.57
    AddTagHelper
    -0.56
     հղումներ
    -0.54
    awtextra
    -0.53
     AttributeSet
    -0.50
    RegistryLite
    -0.50
    EndInit
    -0.49
    POSITIVE LOGITS
     الوطنيه
    0.58
    StateToProps
    0.56
     hourly
    0.56
    Filmografie
    0.52
     Hourly
    0.50
    ToProps
    0.49
    سطس
    0.49
    SafeMath
    0.48
     '\\;'
    0.47
     dew
    0.46
    Activations Density 0.002%

    No Known Activations