© 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. 77828
    Prev
    Next
    INDEX
    Explanations

    URL domain endings

    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
    AddTagHelper
    -0.75
     resourceCulture
    -0.69
    KURZBESCHREIBUNG
    -0.67
    SerializedName
    -0.66
    ClientSize
    -0.63
    CPtr
    -0.63
    UnsafeEnabled
    -0.56
    dafx
    -0.55
     sternum
    -0.55
     secretaries
    -0.55
    POSITIVE LOGITS
     !
    0.44
    ]")]
    0.43
    (!__
    0.43
     متعلقه
    0.42
    bootstrapcdn
    0.42
     libremente
    0.42
     đương
    0.42
    !!
    0.41
    ourne
    0.41
     persiste
    0.40
    Activations Density 0.004%

    No Known Activations