© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14400
    Prev
    Next
    INDEX
    Explanations

    important

    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
    GEBURTSDATUM
    -0.78
    principalTable
    -0.66
     onCreateView
    -0.66
    ArrowToggle
    -0.63
    expandindo
    -0.63
     betweenstory
    -0.61
    ########.
    -0.59
    }))
    -0.59
    ніципа
    -0.57
     GeoNames
    -0.57
    POSITIVE LOGITS
     object
    0.53
     condition
    0.53
    期刊论文
    0.52
     hjelp
    0.51
    contentView
    0.50
    opponent
    0.50
     position
    0.49
    GHIJKLM
    0.49
    beginPath
    0.48
    inação
    0.48
    Activations Density 0.028%

    No Known Activations