© 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. 41815
    Prev
    Next
    INDEX
    Explanations

    whom

    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
     whom
    -3.05
    whom
    -2.63
     Whom
    -2.08
    Whom
    -1.78
     whome
    -1.20
     whoſe
    -1.08
     whofe
    -1.07
     avoient
    -1.05
     Efq
    -0.96
    Datuak
    -0.94
    POSITIVE LOGITS
     it
    0.91
     I
    0.86
     we
    0.83
     there
    0.76
     the
    0.76
    s
    0.71
    ly
    0.70
     you
    0.68
     he
    0.67
     they
    0.66
    Activations Density 0.229%

    No Known Activations