© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94458
    Prev
    Next
    INDEX
    Explanations

    Time or order

    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
     terms
    -0.53
     !$
    -0.50
     $]$
    -0.47
    }}/>
    -0.47
     dita
    -0.46
     comments
    -0.46
    !*\
    -0.46
    ]$
    -0.45
    ]<=
    -0.44
    IBLE
    -0.44
    POSITIVE LOGITS
     propOrder
    0.91
    tagHelperRunner
    0.90
     initComponents
    0.68
    throughout
    0.63
     muualla
    0.62
    StructEnd
    0.62
     väg
    0.60
     vägen
    0.60
    __(/*!
    0.58
    IsPostBack
    0.58
    Activations Density 0.002%

    No Known Activations