© 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. 5-CLT-HP
    7. 4505
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
     Commencez
    -0.64
    cheibe
    -0.62
    StoryboardSegue
    -0.59
    ScopeManager
    -0.56
    getSystemService
    -0.55
    StructEnd
    -0.53
    DECREF
    -0.53
    蚪
    -0.53
     imidlertid
    -0.52
    Bronnen
    -0.51
    POSITIVE LOGITS
    ered
    0.56
    piece
    0.56
    outh
    0.52
    ouse
    0.52
    ance
    0.52
    ment
    0.51
    sions
    0.51
     nonatomic
    0.51
    tional
    0.50
     contextLoads
    0.50
    Activations Density 0.006%

    No Known Activations