© 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. 5-CLT-HP
    7. 91663
    Prev
    Next
    INDEX
    Explanations

    Conversational text

    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
     parcheggio
    -0.63
    PYX
    -0.57
     tarjo
    -0.56
     answer
    -0.53
    ighed
    -0.52
    Personendaten
    -0.52
     élabor
    -0.52
     starve
    -0.51
    ñores
    -0.51
     build
    -0.51
    POSITIVE LOGITS
     realization
    0.53
     different
    0.52
    UnusedPrivate
    0.51
    CopyWith
    0.50
     extradition
    0.49
     Different
    0.49
     Rosewood
    0.49
    {/
    0.48
     robotics
    0.48
     realisation
    0.47
    Activations Density 0.001%

    No Known Activations