© 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. 92228
    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
    tschaft
    -0.63
    énario
    -0.59
     IEnumerator
    -0.54
    ngths
    -0.51
    MeasureSpec
    -0.50
    خواهد
    -0.50
     BoxFit
    -0.50
    atement
    -0.50
    ness
    -0.49
    itinéraire
    -0.48
    POSITIVE LOGITS
    expandindo
    0.63
     ligiloj
    0.62
    WithIOException
    0.60
    IVEREF
    0.59
    <bos>
    0.57
    )))));
    0.56
     uintptr
    0.53
    }}">
    0.53
    abstractmethod
    0.53
     néz
    0.53
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.