© 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. 4293
    Prev
    Next
    INDEX
    Explanations

    frm

    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
    Advertisement
    -0.41
    Хьажоргаш
    -0.40
     estimés
    -0.37
    esque
    -0.37
     fertig
    -0.37
    isme
    -0.36
    🇧
    -0.35
    ابی
    -0.34
     kun
    -0.34
    kla
    -0.34
    POSITIVE LOGITS
     GenerationType
    0.75
     chng
    0.73
     Mgr
    0.70
    }))
    0.70
     typelib
    0.69
    awtextra
    0.67
    GOTREF
    0.67
    Blk
    0.65
    WebVitals
    0.64
    Fns
    0.64
    Activations Density 0.019%

    No Known Activations