© 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. 72959
    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
     ddelweddau
    -0.63
    ]")]
    -0.53
    SourceChecksum
    -0.52
    DebuggerNonUser
    -0.49
     SOCK
    -0.48
    localctx
    -0.47
    orszá
    -0.46
    πομπ
    -0.46
    DrawerToggle
    -0.46
    äsenti
    -0.45
    POSITIVE LOGITS
     mourut
    0.59
    unnitel
    0.54
     CURIAM
    0.52
     correctes
    0.52
    taines
    0.51
     }>
    0.50
    Amicalement
    0.49
     laude
    0.49
    MENAFN
    0.48
    ']):
    0.48
    Activations Density 0.007%

    No Known Activations