© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96246
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     himſelf
    -0.73
    ?')
    -0.73
     Jefus
    -0.73
     Majefty
    -0.68
     мәкал
    -0.68
     Roskov
    -0.68
     myſelf
    -0.66
     themſelves
    -0.66
     houſe
    -0.65
    ?")
    -0.65
    POSITIVE LOGITS
    JAXB
    0.53
    phins
    0.50
    ServletException
    0.47
    OwnProperty
    0.45
    fattning
    0.44
    A
    0.44
    定了
    0.44
    offsetTop
    0.43
     aj
    0.42
    clientHeight
    0.42
    Activations Density 0.000%

    No Known Activations