© 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. 0-CLT-HP
    7. 94941
    Prev
    Next
    INDEX
    Explanations

    bonding

    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
     bonding
    -0.83
    bonded
    -0.82
     bond
    -0.82
    bonding
    -0.81
     bonded
    -0.79
     Bonding
    -0.74
     Swelling
    -0.74
    bond
    -0.72
     solidly
    -0.71
     swelling
    -0.68
    POSITIVE LOGITS
    LookAnd
    0.76
    iness
    0.63
    iann
    0.58
    BeginContext
    0.58
    isms
    0.57
     betweenstory
    0.56
    iest
    0.55
    istic
    0.54
    ities
    0.53
    ########.
    0.53
    Activations Density 0.800%

    No Known Activations