© 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. 1-CLT-HP
    7. 971
    Prev
    Next
    INDEX
    Explanations

    Support and aid

    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
    териал
    -0.56
    पया
    -0.54
     joaat
    -0.49
     öns
    -0.48
    peutic
    -0.48
    ilitary
    -0.47
    ніципалі
    -0.47
    FormState
    -0.47
    下载附件
    -0.47
     balik
    -0.47
    POSITIVE LOGITS
     checks
    0.58
     betweenstory
    0.56
    SharedDtor
    0.53
     belongs
    0.53
    SharedCtor
    0.51
    ArgsConstructor
    0.49
     CommonModule
    0.49
     checked
    0.47
     hangs
    0.47
     المعيارى
    0.47
    Activations Density 0.017%

    No Known Activations