© 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. 5-CLT-HP
    7. 94939
    Prev
    Next
    INDEX
    Explanations

    criteria

    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
    fromCharCode
    -0.62
     informée
    -0.61
     esternos
    -0.61
     विश्वसनीयता
    -0.61
    batore
    -0.60
    PreAuthorize
    -0.60
    UVWXYZ
    -0.59
     springfox
    -0.59
    expandindo
    -0.58
    хьтан
    -0.57
    POSITIVE LOGITS
    es
    0.59
     وتسجيلات
    0.50
    '
    0.49
    ’
    0.48
    etzt
    0.47
     owes
    0.41
    条
    0.41
    ıt
    0.40
     loi
    0.40
    verläs
    0.40
    Activations Density 0.002%

    No Known Activations