© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15643
    Prev
    Next
    INDEX
    Explanations

    called

    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
     the
    -0.55
     therefore
    -0.51
     had
    -0.51
     although
    -0.49
    그러나
    -0.49
     frente
    -0.47
    러나
    -0.47
    Sedangkan
    -0.47
     ]
    -0.46
    latego
    -0.45
    POSITIVE LOGITS
    ⓧ
    0.74
     supérieurs
    0.67
     Dreyfus
    0.66
    FieldBuilder
    0.66
    EDEFAULT
    0.64
    MessageState
    0.64
     ligiloj
    0.63
     Giver
    0.62
     Guiana
    0.61
     Inferior
    0.61
    Activations Density 0.011%

    No Known Activations