© 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. 20-CLT-HP
    7. 76676
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    IntoConstraints
    -0.83
    Aholisi
    -0.71
    delwed
    -0.68
     nakalista
    -0.66
     Theſe
    -0.65
     Jefus
    -0.65
     ſmall
    -0.65
     Monfieur
    -0.65
     ſame
    -0.64
    oucí
    -0.64
    POSITIVE LOGITS
    Decided
    0.52
     led
    0.49
     controls
    0.48
     does
    0.47
     is
    0.45
     did
    0.45
     went
    0.44
     caused
    0.44
    Lähteet
    0.42
     came
    0.42
    Activations Density 0.000%

    No Known Activations