© 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. 5-CLT-HP
    7. 91830
    Prev
    Next
    INDEX
    Explanations

    traumatic events

    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
     Experiences
    -0.56
     Erfahrung
    -0.56
    Exper
    -0.56
     experiences
    -0.54
    ArgsConstructor
    -0.52
     experience
    -0.52
    experiences
    -0.50
    past
    -0.50
    Hozzáférés
    -0.50
    sla
    -0.49
    POSITIVE LOGITS
    SerializedSize
    0.66
    reportWebVitals
    0.59
    rpn
    0.59
    assertIs
    0.57
    andos
    0.55
     Houſe
    0.55
    cèse
    0.54
     createSlice
    0.54
    krivelse
    0.54
    Parabéns
    0.53
    Activations Density 0.002%

    No Known Activations