© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92852
    Prev
    Next
    INDEX
    Explanations

    again

    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
     again
    -0.75
     Again
    -0.71
    Again
    -0.70
     novamente
    -0.65
     taas
    -0.64
    again
    -0.61
     infine
    -0.58
     schließlich
    -0.56
     AGAIN
    -0.55
     nuevamente
    -0.55
    POSITIVE LOGITS
     cref
    0.70
    s
    0.69
    BASEPATH
    0.66
    os
    0.63
    ContentAsync
    0.60
    <eos>
    0.57
     bross
    0.57
    '
    0.57
    </strong>
    0.56
    age
    0.56
    Activations Density 0.022%

    No Known Activations