© 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. 42514
    Prev
    Next
    INDEX
    Explanations

    make

    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
     make
    -2.34
    make
    -2.05
     Make
    -1.95
    Make
    -1.92
     makes
    -1.84
     making
    -1.67
     MAKE
    -1.56
    MAKE
    -1.43
    making
    -1.38
    makes
    -1.38
    POSITIVE LOGITS
     Efq
    1.27
     Monfieur
    1.23
     ſeveral
    1.16
     myſelf
    1.13
     faſt
    1.11
     Theſe
    1.11
     iſt
    1.07
     Jefus
    1.07
    principalColumn
    1.06
     poffible
    1.06
    Activations Density 0.231%

    No Known Activations