© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95247
    Prev
    Next
    INDEX
    Explanations

    intentions

    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
     Efq
    -1.21
     Monfieur
    -1.04
     Anſ
    -0.95
     purpoſe
    -0.93
     iſt
    -0.91
     Jefus
    -0.91
     myſelf
    -0.91
     becauſe
    -0.88
     photolibrary
    -0.88
     Majefty
    -0.88
    POSITIVE LOGITS
    ↵
    0.82
     of
    0.63
     I
    0.63
      
    0.61
    ↵↵
    0.60
    <eos>
    0.59
     is
    0.58
     The
    0.58
    MarshalTo
    0.57
     mergeFrom
    0.56
    Activations Density 0.161%

    No Known Activations