© 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. 91967
    Prev
    Next
    INDEX
    Explanations

    Storage and Economics

    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
     iſt
    -0.84
     Monfieur
    -0.83
     Theſe
    -0.81
     Houſe
    -0.80
     itſelf
    -0.80
     ―――――
    -0.80
     doubtnut
    -0.79
    ſelves
    -0.79
     sauvages
    -0.78
     myſelf
    -0.78
    POSITIVE LOGITS
    ilever
    0.55
     en
    0.49
    pacho
    0.49
    newArrayList
    0.47
     Z
    0.45
    <tbody>
    0.45
    putExtra
    0.45
    <eos>
    0.45
    
    0.44
     S
    0.44
    Activations Density 0.135%

    No Known Activations