© 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. 1-CLT-HP
    7. 14629
    Prev
    Next
    INDEX
    Explanations

    encyclopedia snippets

    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
    TagMode
    -0.52
    And
    -0.47
    ma
    -0.46
    eg
    -0.46
     ancianos
    -0.45
    ja
    -0.45
     cielos
    -0.44
    //
    -0.43
     Preferencias
    -0.43
     plais
    -0.43
    POSITIVE LOGITS
     myſelf
    0.81
     purpoſe
    0.81
     Monfieur
    0.78
     pleaſure
    0.77
     Molière
    0.75
     houſe
    0.74
    ſelves
    0.74
    \<^
    0.69
     ſever
    0.68
     Majefty
    0.68
    Activations Density 0.001%

    No Known Activations