© 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. 4-CLT-HP
    7. 487
    Prev
    Next
    INDEX
    Explanations

    technical/academic 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
    epam
    -0.68
    ROIT
    -0.65
     ffilmiau
    -0.61
    elsey
    -0.60
     vuitton
    -0.59
    surate
    -0.58
    avao
    -0.58
    faser
    -0.57
    ]--;
    -0.57
     cherchés
    -0.56
    POSITIVE LOGITS
     mean
    0.60
    mean
    0.47
     ProtoMessage
    0.47
     on
    0.46
     bonus
    0.45
    ★★★★
    0.45
     noDo
    0.43
     Buddha
    0.43
     GenerationType
    0.43
     Mean
    0.42
    Activations Density 0.022%

    No Known Activations