© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13331
    Prev
    Next
    INDEX
    Explanations

    uman

    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
    EndContext
    -0.90
     purpoſe
    -0.88
     raiſ
    -0.85
     fubject
    -0.85
     ſche
    -0.84
     ſta
    -0.83
     houſe
    -0.81
     fevere
    -0.81
     ſmall
    -0.80
     ſtate
    -0.79
    POSITIVE LOGITS
     PH
    0.51
     hu
    0.50
     HO
    0.47
     H
    0.47
    s
    0.44
     Ho
    0.44
    ,
    0.43
     iniziato
    0.43
    ’
    0.42
     long
    0.42
    Activations Density 0.043%

    No Known Activations