© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97854
    Prev
    Next
    INDEX
    Explanations

    Calls to action

    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
    InjectAttribute
    -0.79
    kloped
    -0.74
    enumii
    -0.70
    yntaxException
    -0.62
     թվական
    -0.60
    ConstraintMaker
    -0.59
    ($__
    -0.59
     wikipagina
    -0.59
    Hochspringen
    -0.57
     utafitiHapana
    -0.57
    POSITIVE LOGITS
     here
    0.56
    сюда
    0.51
     us
    0.50
    :
    0.50
     Class
    0.49
     below
    0.48
     zde
    0.47
    medskip
    0.45
    省市镇
    0.44
    Fq
    0.44
    Activations Density 0.005%

    No Known Activations