© 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. 1-CLT-HP
    7. 14488
    Prev
    Next
    INDEX
    Explanations

    shelter

    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
     Shelter
    -1.10
     shelter
    -1.09
     sheltered
    -1.07
    shelter
    -0.96
    Shelter
    -0.94
     Shel
    -0.85
     shelters
    -0.84
     SHEL
    -0.84
    shel
    -0.81
    Shel
    -0.63
    POSITIVE LOGITS
    ThroughAttribute
    0.84
    EditorBrowsable
    0.74
    rungsseite
    0.74
    belt
    0.65
    belts
    0.64
     AssemblyVersion
    0.63
     resourceCulture
    0.60
    chafft
    0.60
    //
    0.59
    bag
    0.58
    Activations Density 0.007%

    No Known Activations