© 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. 4-CLT-HP
    7. 3314
    Prev
    Next
    INDEX
    Explanations

    computer-related content

    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
     ...
    -0.39
    __*/
    -0.36
     !
    -0.35
    %">
    -0.35
    ...
    -0.35
     himo
    -0.35
    <eos>
    -0.34
    igshid
    -0.34
     Picchu
    -0.33
    jana
    -0.33
    POSITIVE LOGITS
     myſelf
    0.88
     Efq
    0.88
    <bos>
    0.87
     Monfieur
    0.86
     whoſe
    0.84
     becauſe
    0.82
     purpoſe
    0.79
     ſche
    0.78
     houſe
    0.76
     uſed
    0.76
    Activations Density 0.000%

    No Known Activations