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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97962
    Prev
    Next
    INDEX
    Explanations

    Larry

    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
    -1.26
     Theſe
    -1.23
     ſeveral
    -1.16
     Monfieur
    -1.13
     itſelf
    -1.10
     poffe
    -1.09
     themſelves
    -1.07
     Jefus
    -1.07
    Personensuche
    -1.06
     raiſ
    -1.05
    POSITIVE LOGITS
     be
    0.84
    f
    0.71
     f
    0.60
    -
    0.58
    in
    0.57
     l
    0.56
    p
    0.54
    ,
    0.54
     tem
    0.54
    v
    0.54
    Activations Density 0.150%

    No Known Activations