© 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. 4864
    Prev
    Next
    INDEX
    Explanations

    i

    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
     linearly
    -0.55
    dbf
    -0.55
    tacular
    -0.52
    initComponents
    -0.52
    makeConstraints
    -0.51
    zerű
    -0.50
     unid
    -0.50
    })));
    -0.48
    pinephrine
    -0.48
     viscose
    -0.48
    POSITIVE LOGITS
     avoient
    0.59
     intérêt
    0.58
     invokingState
    0.54
     PeEnEo
    0.54
     étoient
    0.53
    bootstrapcdn
    0.53
    aarrggbb
    0.52
    OGND
    0.52
     kabát
    0.51
    cogn
    0.51
    Activations Density 0.001%

    No Known Activations