© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94232
    Prev
    Next
    INDEX
    Explanations

    environmental issues

    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
    
    -1.11
    .*")]
    -0.84
    +#+
    -0.82
    +#+#
    -0.82
    OGND
    -0.78
     Monfieur
    -0.78
     EconPapers
    -0.77
     whistles
    -0.73
     ***!
    -0.73
     Houſe
    -0.72
    POSITIVE LOGITS
    s
    0.49
    i
    0.45
    seiti
    0.44
    sp
    0.42
    als
    0.41
    ی
    0.40
    ss
    0.39
    ssons
    0.39
    aap
    0.38
    ‌ها
    0.38
    Activations Density 0.107%

    No Known Activations