© 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. 0-CLT-HP
    7. 43727
    Prev
    Next
    INDEX
    Explanations

    Elementary

    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
     strength
    -1.13
    strength
    -1.03
     Strength
    -0.89
     elementary
    -0.81
    Strength
    -0.77
     Elementary
    -0.76
     STRENGTH
    -0.72
    Elementary
    -0.68
     streng
    -0.62
     styr
    -0.60
    POSITIVE LOGITS
     Majefty
    0.73
     Roskov
    0.71
     Reſ
    0.69
     Efq
    0.66
    ViewInit
    0.65
     doubtnut
    0.65
     myſelf
    0.65
    coste
    0.63
     Мексичка
    0.62
     Diſ
    0.62
    Activations Density 0.541%

    No Known Activations