© 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. 96891
    Prev
    Next
    INDEX
    Explanations

    Extracted data/lists

    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
     ujednoznacz
    -0.92
    rungsseite
    -0.77
     propOrder
    -0.73
    setVerticalGroup
    -0.70
    ✨:
    -0.66
    __':
    -0.64
     يتيمه
    -0.63
    
    -0.63
    verwijspagina
    -0.63
    findpost
    -0.60
    POSITIVE LOGITS
    ,
    0.84
     although
    0.49
     while
    0.48
     not
    0.47
    ầng
    0.46
     teneur
    0.42
    流れ
    0.42
    POSURE
    0.42
    membered
    0.42
     the
    0.41
    Activations Density 0.000%

    No Known Activations