© 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. 4-CLT-HP
    7. 1995
    Prev
    Next
    INDEX
    Explanations

    radiant

    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
    AutoScaleMode
    -0.57
    Tembelea
    -0.56
    httphttps
    -0.51
     >=",
    -0.51
    orth
    -0.51
    ofire
    -0.50
    GIVEREF
    -0.50
     Mao
    -0.49
     resourceCulture
    -0.48
     feroit
    -0.48
    POSITIVE LOGITS
     BoxFit
    0.60
     heat
    0.56
    NamedQuery
    0.55
    Portale
    0.53
    Carriera
    0.52
    thebibliography
    0.51
    posedge
    0.51
    GEBURTSDATUM
    0.51
    ineo
    0.50
    NameInMap
    0.50
    Activations Density 0.001%

    No Known Activations