© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15960
    Prev
    Next
    INDEX
    Explanations

    key

    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
    key
    -0.57
     key
    -0.52
    itattu
    -0.50
    gameserver
    -0.49
    KEY
    -0.49
    roupa
    -0.49
     HttpNotFound
    -0.47
     labouring
    -0.47
    キー
    -0.46
    labour
    -0.46
    POSITIVE LOGITS
    Datuak
    0.66
    })()
    0.64
    utilisons
    0.54
    oczes
    0.54
     }))
    0.51
    astify
    0.51
     ]
    0.50
    Extinguishing
    0.50
    Hozzáférés
    0.49
    __':
    0.49
    Activations Density 0.069%

    No Known Activations