© 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. 20-CLT-HP
    7. 73297
    Prev
    Next
    INDEX
    Explanations

    Formal and Legalistic texts

    np_max-act-logits · 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
     JpaRepository
    -0.93
     utafitiHapana
    -0.87
    PerformLayout
    -0.85
    mybatisplus
    -0.84
    TestingModule
    -0.81
     समीक्षक
    -0.76
    \{\\
    -0.75
     estekak
    -0.75
    ]")]
    -0.75
    enderror
    -0.74
    POSITIVE LOGITS
     about
    0.54
     for
    0.46
     done
    0.44
     nothing
    0.44
     viewed
    0.43
     there
    0.43
     a
    0.43
     looked
    0.43
     strictly
    0.41
     used
    0.41
    Activations Density 0.000%

    No Known Activations