© 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. 3433
    Prev
    Next
    INDEX
    Explanations

    Form and structure

    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
    AndEndTag
    -0.64
    RepeatedField
    -0.63
    tvguidetime
    -0.59
    InitVars
    -0.58
     OnTrigger
    -0.55
     archipelago
    -0.54
     Lijst
    -0.54
    porte
    -0.54
    Geplaatst
    -0.54
    sorption
    -0.54
    POSITIVE LOGITS
     Nacionales
    0.52
     fallu
    0.51
    __":
    0.50
     interiores
    0.49
     للمعارف
    0.47
     classiques
    0.47
     gesucht
    0.47
    הערות
    0.47
     juger
    0.46
    MLLoader
    0.46
    Activations Density 0.001%

    No Known Activations