© 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. 93076
    Prev
    Next
    INDEX
    Explanations

    science/technical

    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
    O
    -0.45
     custodia
    -0.42
     est
    -0.42
    -
    -0.41
    itinéraire
    -0.41
     back
    -0.40
     parar
    -0.40
     paljon
    -0.40
    いかに
    -0.39
    R
    -0.39
    POSITIVE LOGITS
    StoryboardSegue
    0.98
     betweenstory
    0.93
    tvguidetime
    0.91
     مشين
    0.90
    __':
    0.90
     Theſe
    0.88
    __":
    0.84
    CPtr
    0.81
    ItemBackground
    0.81
     myſelf
    0.81
    Activations Density 0.003%

    No Known Activations