© 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. 91781
    Prev
    Next
    INDEX
    Explanations

    events and achievements

    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
     ComVisible
    -0.47
    els
    -0.46
    уза
    -0.46
    ValueStyle
    -0.45
    zik
    -0.43
    uz
    -0.43
    っていたので
    -0.43
    nonatomic
    -0.43
    NameValuePair
    -0.42
     ujednoznacz
    -0.42
    POSITIVE LOGITS
    клопе
    0.71
     itſelf
    0.66
    ]")]
    0.66
    NUMX
    0.65
    reportWebVitals
    0.61
    Personendaten
    0.60
    PointerException
    0.59
    Diweddarwch
    0.57
     Reverso
    0.56
    };*/
    0.56
    Activations Density 0.018%

    No Known Activations