© 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. 94649
    Prev
    Next
    INDEX
    Explanations

    Property

    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
     dõi
    -0.55
     Handle
    -0.55
     Komunikasi
    -0.54
    NewUrlParser
    -0.54
    IVEREF
    -0.52
     digress
    -0.52
    обходи
    -0.51
    igshid
    -0.51
     natale
    -0.51
    lify
    -0.50
    POSITIVE LOGITS
    WebElementEntity
    0.65
    owning
    0.58
     rights
    0.56
     ownership
    0.55
    ReusableCell
    0.53
    |}{$
    0.52
     jspb
    0.52
     property
    0.52
     right
    0.51
     law
    0.50
    Activations Density 0.002%

    No Known Activations