© 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. 5-CLT-HP
    4. 361
    Prev
    Next
    INDEX
    Explanations

    ;

    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
    istoitu
    -0.52
     IndexPath
    -0.50
    styleUrls
    -0.47
    NSIndexPath
    -0.44
    def
    -0.44
     the
    -0.43
    JoinTable
    -0.43
    <?
    -0.43
    umsi
    -0.42
     entries
    -0.42
    POSITIVE LOGITS
    Autoritní
    0.80
    yntaxException
    0.70
    NameInMap
    0.65
     magnesium
    0.64
     castor
    0.63
     cashmere
    0.60
     PopupWindow
    0.60
     EconPapers
    0.59
    imothy
    0.58
    Архівовано
    0.58
    Activations Density 0.000%

    No Known Activations