© 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. 0-CLT-HP
    4. 91070
    Prev
    Next
    INDEX
    Explanations

    seem

    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
    -6.78
     itſelf
    -6.47
     Efq
    -6.41
     Monfieur
    -6.06
     Majefty
    -6.00
     pleaſure
    -5.88
     Jefus
    -5.81
     ―――――
    -5.78
     Theſe
    -5.75
    ſelf
    -5.63
    POSITIVE LOGITS
     
    3.66
    .
    3.44
    ,
    3.44
     (
    3.22
    ↵↵
    3.17
    ↵
    3.13
    <eos>
    2.92
    '
    2.92
     "
    2.78
    -
    2.77
    Activations Density 0.036%

    No Known Activations