© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93221
    Prev
    Next
    INDEX
    Explanations

    Provider

    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
    antaranya
    -0.60
    pement
    -0.55
     HasFactory
    -0.54
    miento
    -0.50
    QUES
    -0.49
    cension
    -0.49
    ]--;
    -0.48
    ought
    -0.48
    HOUT
    -0.47
    وعة
    -0.47
    POSITIVE LOGITS
     surla
    0.64
    ỡng
    0.56
     pinulongan
    0.53
    ########.
    0.53
     AssemblyTitle
    0.52
    adə
    0.52
    AllowUser
    0.50
    Hochspringen
    0.49
     ComVisible
    0.49
    FormTagHelper
    0.49
    Activations Density 0.000%

    No Known Activations