© 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. 5-CLT-HP
    7. 4849
    Prev
    Next
    INDEX
    Explanations

    software/programming errors

    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
    IUrlHelper
    -0.64
    GTCX
    -0.49
     Sodom
    -0.44
    lø
    -0.43
     Diony
    -0.43
     chileno
    -0.42
     Biôgrafia
    -0.41
     paranormal
    -0.41
    hdessä
    -0.41
     turbid
    -0.40
    POSITIVE LOGITS
    PYX
    0.63
     autorytatywna
    0.60
    )];
    0.59
     spreken
    0.59
    ]));
    0.57
    ]))
    0.57
    ]),
    0.56
     AssemblyProduct
    0.56
     calendriers
    0.56
     Platforms
    0.53
    Activations Density 0.064%

    No Known Activations