© 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. 20-CLT-HP
    7. 76262
    Prev
    Next
    INDEX
    Explanations

    want

    np_max-act-logits · 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
    ┐
    -0.61
    groom
    -0.51
    GARD
    -0.49
    órmula
    -0.48
    Nonnull
    -0.47
    
    -0.46
     Fat
    -0.46
    VertexArray
    -0.46
    })$}
    -0.45
    SerializeField
    -0.45
    POSITIVE LOGITS
     want
    1.45
    want
    1.20
     Want
    1.17
     wants
    1.15
     wanna
    1.12
    Want
    1.05
     WANT
    1.05
     wanted
    0.95
    wants
    0.95
     wanting
    0.90
    Activations Density 0.000%

    No Known Activations