© 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. 4710
    Prev
    Next
    INDEX
    Explanations

    childhood memories

    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
    principalTable
    -0.54
    bonucle
    -0.52
    setVerticalGroup
    -0.52
    DialogTitle
    -0.50
    providedIn
    -0.50
     De
    -0.50
    루
    -0.50
     onPostExecute
    -0.48
     trev
    -0.48
    رج
    -0.47
    POSITIVE LOGITS
     comigo
    0.59
    hoeddwyd
    0.54
    Демографія
    0.53
     WebDriverWait
    0.53
    fillType
    0.53
     vägen
    0.53
     Nós
    0.52
    ándome
    0.52
     houſe
    0.51
     growing
    0.51
    Activations Density 0.004%

    No Known Activations