© 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. 39781
    Prev
    Next
    INDEX
    Explanations

    converters and regulating

    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
    y
    -0.99
    s
    -0.89
    ar
    -0.65
    l
    -0.65
    en
    -0.64
    le
    -0.62
    t
    -0.62
    b
    -0.62
    er
    -0.58
    sg
    -0.58
    POSITIVE LOGITS
     Reſ
    1.03
     Efq
    0.99
     myſelf
    0.97
    HostException
    0.93
     ―――――
    0.88
     itſelf
    0.88
     ſtate
    0.88
     purpoſe
    0.84
     Anſ
    0.82
     Inſ
    0.82
    Activations Density 1.678%

    No Known Activations