© 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. 42801
    Prev
    Next
    INDEX
    Explanations

    succeed

    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
     succeed
    -1.47
    succeed
    -1.05
     Success
    -1.03
     succeeds
    -1.03
     succeeding
    -0.99
     success
    -0.93
     Suc
    -0.88
     succeeded
    -0.82
    Success
    -0.79
    succeeded
    -0.72
    POSITIVE LOGITS
     itſelf
    0.79
     purpoſe
    0.77
     himſelf
    0.69
     leſs
    0.69
     fhort
    0.68
     myſelf
    0.67
     pleaſure
    0.66
     poffe
    0.66
     Houſe
    0.65
     themſelves
    0.64
    Activations Density 0.079%

    No Known Activations