Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39773
    Prev
    Next
    INDEX
    Explanations

    devastation

    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
     myſelf
    -1.38
    +#+#
    -1.24
     CreateTagHelper
    -1.23
     Efq
    -1.21
     Monfieur
    -1.21
     purpoſe
    -1.12
     Majefty
    -1.12
     propOrder
    -1.09
    esterday
    -1.08
     Jefus
    -1.08
    POSITIVE LOGITS
    n
    0.83
    sp
    0.78
    ers
    0.75
    se
    0.70
    z
    0.70
    ss
    0.69
    ness
    0.68
    sw
    0.68
    .
    0.66
    ment
    0.66
    Activations Density 0.984%

    No Known Activations