© 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. 358
    Prev
    Next
    INDEX
    Explanations

    formal language

    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
     poffe
    -0.68
     paſſ
    -0.65
     greateſt
    -0.64
     abſ
    -0.62
     raiſ
    -0.61
     whoſe
    -0.60
     الحره
    -0.59
     Tasse
    -0.58
     abnormalities
    -0.58
     beſ
    -0.58
    POSITIVE LOGITS
    +#+#
    0.60
     Paglinawan
    0.54
     encarga
    0.53
    DebuggerNonUser
    0.51
     or
    0.51
    tvguidetime
    0.50
    
    0.50
    XmlAccessType
    0.49
     jScrollPane
    0.47
    BagLayout
    0.47
    Activations Density 0.014%

    No Known Activations