© 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. 20-CLT-HP
    7. 75552
    Prev
    Next
    INDEX
    Explanations

    ily

    np_max-act-logits · 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
    StreetMap
    -0.96
     Италијани
    -0.95
     Administrativna
    -0.89
    Espèce
    -0.85
    脚注の使い方
    -0.85
     ligiloj
    -0.80
    Παραπομπές
    -0.80
     BoxFit
    -0.80
    NUMX
    -0.78
     distanciation
    -0.78
    POSITIVE LOGITS
     similar
    0.63
     the
    0.51
    般
    0.44
    the
    0.42
    similar
    0.42
    isfile
    0.41
     ähnlich
    0.35
     sé
    0.32
     alike
    0.32
    ling
    0.32
    Activations Density 0.001%

    No Known Activations