© 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. 4516
    Prev
    Next
    INDEX
    Explanations

    Dates and Times

    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
    SequentialGroup
    -0.59
    ודם
    -0.58
    tagHelperRunner
    -0.56
    None
    -0.53
     esternos
    -0.52
     None
    -0.52
     transfieras
    -0.51
     оригіналу
    -0.50
     NONE
    -0.50
    ()}>
    -0.49
    POSITIVE LOGITS
    GrantedAuthority
    0.56
    lidays
    0.54
     soste
    0.52
     sekarang
    0.52
     tavola
    0.51
    .
    0.51
    ruptedException
    0.49
    .[/
    0.48
    .•
    0.48
     now
    0.48
    Activations Density 0.003%

    No Known Activations