© 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. 5-CLT-HP
    7. 93461
    Prev
    Next
    INDEX
    Explanations

    removed

    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
     had
    -0.84
     could
    -0.82
     was
    -0.78
     hadn
    -0.72
     were
    -0.71
     seemed
    -0.71
     knew
    -0.71
     wasn
    -0.68
     depended
    -0.68
     pouvaient
    -0.68
    POSITIVE LOGITS
    InputBorder
    0.68
    Personendaten
    0.67
     scolas
    0.63
    kloped
    0.62
    NUMX
    0.61
     Spisak
    0.60
     purpoſe
    0.59
    ίναι
    0.59
     perfons
    0.58
     umana
    0.58
    Activations Density 0.002%

    No Known Activations