© 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. 41627
    Prev
    Next
    INDEX
    Explanations

    End of a process

    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
    Afterwards
    -0.84
     subsequently
    -0.79
     subsequent
    -0.79
     afterwards
    -0.78
     posteriormente
    -0.77
    InitVars
    -0.77
     berikutnya
    -0.75
     later
    -0.74
     تضيفلها
    -0.73
    parsedMessage
    -0.73
    POSITIVE LOGITS
    n
    0.53
    t
    0.53
    ctive
    0.52
     prolongation
    0.51
    hdys
    0.50
     Desi
    0.49
     المنا
    0.49
     Needle
    0.49
     Sienna
    0.48
    tive
    0.48
    Activations Density 0.161%

    No Known Activations