© 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. 73154
    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
    ']")
    -0.50
     })}
    -0.49
     Share
    -0.48
     Ball
    -0.47
    saraba
    -0.47
     ]:
    -0.45
    $}}
    -0.45
     Poll
    -0.44
     aport
    -0.43
     Port
    -0.43
    POSITIVE LOGITS
    tagHelperRunner
    0.74
    zzleHttp
    0.69
     reve
    0.68
     gob
    0.68
    +#+#
    0.62
     CreateTagHelper
    0.61
    gdx
    0.59
     Roskov
    0.59
    rrggbb
    0.58
     otomatig
    0.58
    Activations Density 0.001%

    No Known Activations