© 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. 0-CLT-HP
    7. 93740
    Prev
    Next
    INDEX
    Explanations

    else

    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
     else
    -1.27
    else
    -1.22
     firm
    -1.04
    ELSE
    -0.68
    nya
    -0.68
     Else
    -0.65
     ELSE
    -0.65
    Else
    -0.62
    ly
    -0.57
    elif
    -0.57
    POSITIVE LOGITS
     Cæsar
    0.97
     Efq
    0.91
     photolibrary
    0.85
    ſelf
    0.84
     Anſ
    0.82
     Theſe
    0.81
     Monfieur
    0.79
     $_"
    0.79
     Forumite
    0.77
     myſelf
    0.77
    Activations Density 0.033%

    No Known Activations