© 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. 0-CLT-HP
    7. 93968
    Prev
    Next
    INDEX
    Explanations

    considered

    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
    considered
    -0.88
     considered
    -0.84
     considerado
    -0.82
     considers
    -0.80
     Considered
    -0.79
    Consider
    -0.77
     CONSIDER
    -0.76
     considerados
    -0.75
     consider
    -0.74
     considéré
    -0.73
    POSITIVE LOGITS
     “
    0.59
    IBOutlet
    0.59
     "
    0.59
     total
    0.56
     to
    0.53
    CPtr
    0.53
     paid
    0.53
     cost
    0.51
     anti
    0.50
     cref
    0.49
    Activations Density 0.072%

    No Known Activations