© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 42898
    Prev
    Next
    INDEX
    Explanations

    Biological suffixes

    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
    iformis
    -1.04
    ospor
    -1.02
    ifoli
    -1.02
    ophylla
    -1.00
    obacterium
    -0.97
    ifolium
    -0.96
    ophenyl
    -0.94
    obenzene
    -0.93
    actylus
    -0.93
    æa
    -0.92
    POSITIVE LOGITS
    <bos>
    0.56
    évaluateur
    0.52
     »)
    0.51
    <em>
    0.50
    )">
    0.50
    )':
    0.49
    )":
    0.49
    ]}"
    0.49
     Idem
    0.48
     nahilalakip
    0.47
    Activations Density 1.426%

    No Known Activations