© 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. 1-CLT-HP
    7. 10955
    Prev
    Next
    INDEX
    Explanations

    to

    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
    })()
    -0.65
    AddTagHelper
    -0.60
     carry
    -0.59
    ]")]
    -0.59
     link
    -0.57
     step
    -0.56
     play
    -0.55
     isolate
    -0.55
    hasis
    -0.54
     devote
    -0.54
    POSITIVE LOGITS
     fhould
    0.68
     mijne
    0.66
     myſelf
    0.62
     intérieure
    0.61
     türlü
    0.61
    Spoljašnje
    0.59
     fermée
    0.59
     magique
    0.59
     vectorielle
    0.57
     stratégique
    0.57
    Activations Density 0.669%

    No Known Activations