© 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. 1-CLT-HP
    7. 11337
    Prev
    Next
    INDEX
    Explanations

    dis

    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
     purpoſe
    -0.51
     whereof
    -0.50
    
    -0.48
    zoon
    -0.47
    mazoo
    -0.45
    espère
    -0.45
     mAh
    -0.45
    মান
    -0.45
     polymorph
    -0.44
    setCharacter
    -0.44
    POSITIVE LOGITS
    +#+#
    0.77
    يكب
    0.63
     awakeFromNib
    0.62
     متعلقه
    0.60
    confirm
    0.58
    principalTable
    0.56
    exitRule
    0.56
    fjspx
    0.56
    })]
    0.56
    InvalidProtocol
    0.54
    Activations Density 0.012%

    No Known Activations