© 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. 4839
    Prev
    Next
    INDEX
    Explanations

    clarification/explanation

    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
    <bos>
    -0.59
    )++;
    -0.55
    times
    -0.52
    ImageContext
    -0.49
     your
    -0.49
    your
    -0.48
    }());
    -0.48
     thiệu
    -0.46
    WebControls
    -0.45
    ніципа
    -0.44
    POSITIVE LOGITS
    ,
    0.81
     I
    0.75
    abstractmethod
    0.65
     lets
    0.62
    MENAFN
    0.62
    :
    0.61
     let
    0.60
    TAWA
    0.58
     slightly
    0.57
     الاطلاع
    0.57
    Activations Density 0.004%

    No Known Activations