© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 39877
    Prev
    Next
    INDEX
    Explanations

    Hoo

    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
     Efq
    -1.24
     Theſe
    -1.18
     Monfieur
    -1.10
    oredCriteria
    -1.10
     myſelf
    -1.09
     Jefus
    -1.09
     Houſe
    -1.09
     كومونز
    -1.00
     يتيمه
    -0.99
     Majefty
    -0.96
    POSITIVE LOGITS
     of
    0.62
    s
    0.52
    crollView
    0.46
     i
    0.43
     sur
    0.43
     (
    0.42
     f
    0.42
    ,
    0.41
     or
    0.41
    port
    0.40
    Activations Density 1.539%

    No Known Activations