© 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. 4-CLT-HP
    4. 5030
    Prev
    Next
    INDEX
    Explanations

    from

    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
     onBind
    -0.60
     Centra
    -0.59
     linkovi
    -0.57
     IAC
    -0.57
    LVANIA
    -0.54
     سكانية
    -0.52
    lorette
    -0.52
    úrate
    -0.52
    ]--;
    -0.51
    Abitanti
    -0.50
    POSITIVE LOGITS
     now
    1.10
     here
    0.91
     the
    0.85
     this
    0.81
     time
    0.79
    now
    0.73
    bootstrapcdn
    0.67
    VIAF
    0.64
     there
    0.63
     Now
    0.63
    Activations Density 0.003%

    No Known Activations