© 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. 1-CLT-HP
    7. 13948
    Prev
    Next
    INDEX
    Explanations

    brush

    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
    bootstrapcdn
    -0.60
    FieldNumber
    -0.46
    âmetros
    -0.43
    WriteBarrier
    -0.40
    vra
    -0.40
    SerializedName
    -0.39
     Br
    -0.39
    Carriera
    -0.39
    KR
    -0.38
    ametri
    -0.38
    POSITIVE LOGITS
     nakalista
    0.68
    Hozzáférés
    0.67
     seats
    0.65
     JOptionPane
    0.62
    stead
    0.61
     snippetHide
    0.60
     myſelf
    0.60
    enoid
    0.60
    AndEndTag
    0.59
    Palmar
    0.58
    Activations Density 0.013%

    No Known Activations