© 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. 93086
    Prev
    Next
    INDEX
    Explanations

    experience

    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
    ington
    -0.49
    UATION
    -0.48
    ()]
    -0.47
    manship
    -0.46
     Goodness
    -0.45
     })}
    -0.44
     with
    -0.43
    INGTON
    -0.43
    vation
    -0.43
     goodness
    -0.43
    POSITIVE LOGITS
    principalColumn
    0.78
    mybatisplus
    0.75
    tvguidetime
    0.73
    OGND
    0.71
    MigrationBuilder
    0.70
    
    0.69
     насељу
    0.68
    verständlich
    0.68
    BindingResult
    0.68
     الدولى
    0.61
    Activations Density 0.003%

    No Known Activations