© 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. 14594
    Prev
    Next
    INDEX
    Explanations

    biological retention/permeability

    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
    fjspx
    -0.81
    UrlResolution
    -0.80
    RetentionPolicy
    -0.70
     defaultstate
    -0.69
    #+#
    -0.69
    ImageContext
    -0.67
     tartalomajánló
    -0.67
    extAlignment
    -0.65
    AsUp
    -0.64
    TestingModule
    -0.63
    POSITIVE LOGITS
    ofo
    0.51
     just
    0.47
    endor
    0.47
    andar
    0.47
    asma
    0.46
    valis
    0.45
    hely
    0.44
    feira
    0.44
     ch
    0.44
     Halls
    0.43
    Activations Density 0.042%

    No Known Activations